Happening @ Michigan https://events.umich.edu/list/rss RSS Feed for Happening @ Michigan Events at the University of Michigan. Departmental Seminar (899): Cong Shi, U-M IOE (April 9, 2020 3:00pm) https://events.umich.edu/event/74123 74123-18541331@events.umich.edu Event Begins: Thursday, April 9, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Network Revenue Management with Online Inverse Batch Gradient Descent Method

Abstract:
We consider a general class of price-based network revenue management problems that a firm aims to maximize revenue from multiple products produced with multiple types of resources endowed with limited inventory over a finite selling season. A salient feature of our problem is that the firm does not know the underlying demand function that maps prices to demand rate, which must be learned from sales data. It is well known that for almost all classes of demand functions, the revenue rate function is not concave in the products' prices but is concave in products' market shares (or price-controlled demand rates). This creates challenges in adopting any stochastic gradient descent based methods in the price space. We propose a novel nonparametric learning algorithm termed online inverse batch gradient descent (IGD) algorithm. For the large scale systems wherein all resources' inventories and the length of the horizon are proportionally scaled by a parameter $k$, we establish a dimension-independent regret bound of $O( k^{4/5} \log k)$. This result is independent of the number of products and resources and works for a continuum action-set prices and the demand functions that are only once differentiable. Our result guarantees the efficacy of both algorithms in the high dimensional systems where the number of products or resources is large and the prices are continuous. (This is a joint work with Dr. Yiwei Chen.)

Bio:
Cong Shi is an associate professor in the Department of Industrial and Operations Engineering at the University of Michigan at Ann Arbor. His main research interests include supply chain management, revenue management, and service operations. He has won the first place in the INFORMS George Nicholson Student Paper Competition, the third place in the INFORMS Junior Faculty Interest Group (JFIG) Paper Competition, and the finalist for the MSOM Data Driven Challenge. He received his Ph.D. in Operations Research from MIT in 2012, and his B.S. in Mathematics from the National University of Singapore in 2007.

]]>
Workshop / Seminar Mon, 06 Apr 2020 13:32:28 -0400 2020-04-09T15:00:00-04:00 2020-04-09T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Cong Shi
SEMINAR: "Diversity, Equity and Inclusion in Operations Research and Analytics: A Research Agenda for Scholarship, Practice and Service" — Michael P. Johnson (September 10, 2020 3:00pm) https://events.umich.edu/event/76449 76449-19717147@events.umich.edu Event Begins: Thursday, September 10, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Diversity, Equity and Inclusion in Operations Research and Analytics: A Research Agenda for Scholarship, Practice and Service

Abstract:
Diversity, equity and inclusion (DEI) refers to strategies and processes that enable organizations to become more reflective of and responsive to identities, values and experiences of different stakeholder groups. Organizations committed to DEI may better fulfill their missions and improve the well-being of their stakeholder groups and of society at large.

In this talk, I will explore the presence of DEI in OR/analytics through an assessment of the profession (the diversity of OR/analytics practitioners) and scholarship (published and emerging work that addresses DEI and related issues). My focus will be on traditionally underrepresented and marginalized groups and communities. I will discuss current and proposed initiatives to support the increased application of DEI principles throughout OR/analytics practice, research and education. I will argue that infusing DEI and social & racial justice principles within OR/analytics can enable our society to become more equitable, more just and more welcoming of people from diverse backgrounds, identities and communities.

Bio:
Michael P. Johnson is Professor and Chair of the Department of Public Policy and Public Affairs at University of Massachusetts Boston. Dr. Johnson’s research focuses on developing decision models and decision support systems to improve operations and strategy design of nonprofit organizations and government agencies. His primary application areas are affordable and assisted housing, community development, climate change response, and diversity, equity and inclusion in the decision sciences. Dr. Johnson has published widely in academic journals of OR/analytics, urban planning, and housing policy. His most recent extended works include a lead-edited volume of curated papers, including INFORMS Editor’s Cut: Diversity and Inclusion: Analytics for Social Impact (INFORMS, 2019), a lead-edited special issue of European Journal of Operational Research on community operational research (Elsevier, 2018) and a lead-authored book, Decision Science for Housing and Community Development: Localized and Evidence‐Based Responses to Distressed Housing and Blighted Communities (Wiley, 2016). His lead-authored book Supporting Shrinkage: Planning and Decision-Making for Legacy Cities (SUNY Press) will appear in Spring 2021. Dr. Johnson earned his PhD from Northwestern University in operations research in 1997 and his bachelor of science from Morehouse College in 1987.

]]>
Workshop / Seminar Fri, 18 Sep 2020 10:54:00 -0400 2020-09-10T15:00:00-04:00 2020-09-10T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Michael P. Johnson
SEMINAR: "Outward Facing Optimization: Operations Research With Impact" — Laura Albert (September 17, 2020 3:00pm) https://events.umich.edu/event/75962 75962-19631732@events.umich.edu Event Begins: Thursday, September 17, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

This seminar is sponsored by the U-M INFORMS Student Chapter.

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Outward Facing Optimization: Operations Research With Impact

Abstract:
Government programs spanning public safety, transportation security, and critical infrastructure protection must deliver essential services by managing risks such as health emergencies, crime, acts of terrorism, and natural disasters. Doing so requires allocating resources in complex systems that span people, processes, vehicles, and critical infrastructure, where many decisions are interrelated.

Government leaders and researchers have been studying how to design and operate public sector systems to manage risk for the last half a century. Although researchers have created a body of knowledge for supporting prescriptive and predictive decisions in the public sector, public safety leaders must continually adapt to address new risks in budget-constrained environments. As a result, many research challenges remain.

In this talk, Dr. Laura Albert will discuss her research that studies how to design and operate public sector systems using optimization methodologies. She will discuss how she has connected theory and modeling to application in applications in the United States ranging from emergency medical services, aviation security, and critical infrastructure protection. She will also discuss how to engage policymakers and the public with research.

Bio:
Laura Albert, Ph.D., is a Professor of Industrial & Systems Engineering and a Harvey D. Spangler Faculty Scholar at the University of Wisconsin-Madison. Her research interests are in the field of operations research, with a particular focus on discrete optimization with application to homeland security and emergency response problems. Dr. Albert’s research has been supported by the National Science Foundation, the Department of Homeland Security, the Department of the Army, and Sandia National Laboratory. She has authored or co-authored 69 publications in archival journals and refereed proceedings. She has been awarded many honors for her research, including the Institute of Industrial and Systems Engineers (IISE) Fellow Award, the INFORMS Impact Prize, four publication awards, a National Science Foundation CAREER award, a Fulbright Award, and a Department of the Army Young Investigator Award. She is a Department Editor for IIE Transactions and is on or has been on six other journal Editorial Boards. Dr. Albert has served on the INFORMS Board as the Vice President for Marketing, Communication, and Outreach and served as the Assistant Dean for Graduate Affairs in the College of Engineering at UW-Madison. She is the author of the blogs “Punk Rock Operations Research” and “Badger Bracketology.” You can find her on twitter at @lauraalbertphd.

]]>
Workshop / Seminar Fri, 18 Sep 2020 10:55:04 -0400 2020-09-17T15:00:00-04:00 2020-09-17T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Laura Albert
SEMINAR: "Drivers’ Allocation of Attention Given Increasingly Autonomous Systems" — Linda Boyle (September 24, 2020 3:00pm) https://events.umich.edu/event/75963 75963-19629763@events.umich.edu Event Begins: Thursday, September 24, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Drivers’ Allocation of Attention Given Increasingly Autonomous Systems

Abstract:
Safe transport requires an understanding of the road user, their intended trip purpose and their perceptions of safety. In today’s driving environment, the human driver needs to continually switch between driving and non-driving activities. They will adapt their behavior and compensate for any perceived risks given changes in the road, weather and traffic environment. As vehicles become increasingly autonomous, human drivers will also become increasingly accustom to the vehicle assuming control and may not attend to the roadway as needed. The attention to safety critical situations is further impacted given increasing interactions with non-driving tasks while traveling. As the number of autonomous systems in our car grows, the driver’s attention to warnings and alerts diminish, making them less ready to take back control of the vehicle when the automation fails. This presentation describes some of the studies conducted to assess changes in drivers’ allocation of attention as they switch between driving and non-driving task over the course of their drive. Individual differences are observed given the type of task and task complexity. The implications of these findings for the design of future cars are discussed in this presentation.

Bio:
Linda Ng Boyle is Professor and Chair of the Industrial & Systems Engineering Department at the University of Washington, Seattle. She has a joint appointment in Civil & Environmental Engineering. She has degrees from the University of Buffalo (BS) and University of Washington (MS, PhD). She is an organizer for the International Symposium on Human Factors in Driving Assessment and co-author of the textbook, “Designing for People: An Introduction to Human Factors Engineering.” Her area of expertise is in human factors and transportation safety.

This event is sponsored by the University of Michigan HFES Student Chapter.

]]>
Workshop / Seminar Wed, 23 Sep 2020 16:45:04 -0400 2020-09-24T15:00:00-04:00 2020-09-24T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Linda Boyle
SEMINAR: "Using Analytics to Plan Reliable Itineraries Across Transportation Networks" — Michael Redmond (October 1, 2020 3:00pm) https://events.umich.edu/event/76011 76011-19653375@events.umich.edu Event Begins: Thursday, October 1, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Using Analytics to Plan Reliable Itineraries Across Transportation Networks

Abstract:
As access to information on transportation options becomes more readily available, the need arises to find modes of travel and itineraries that will be reliable and easy-to-use for travelers. While there is widespread information on cost and scheduled travel time for everything from airlines to ride-hailing services, the work on showing travelers the variation in travel time of these different options is lagging behind.

This work takes into account the uncertainty in travel time across modes of transportation, including flights, driving and public transit. It plans for this uncertainty by recommending reliable itineraries, which are itineraries that get travelers to their destination on time without missing any connections along the way. This research focuses on modeling transportation networks to discover itinerary reliability in situations where the answer may not be readily apparent, such as travel with layovers or missed transfers.

The experimental results show the value that finding these reliable itineraries can have over shortest travel time itineraries that travelers are accustomed to seeing. Also, this reliability metric gives an additional tool for travelers to use during the decision-making process of their trip planning. By making reliable transportation itineraries more transparent to travelers and network planners, it can help convince travelers to choose these modes of transportation in the future and take some of the uncertainty and stress out of travel planning.

Bio:
Michael Redmond recently graduated in Summer 2020 from the University of Iowa with a PhD in Business Analytics with a focus on transportation analytics and stochastic programming. He is an active member in the Transportation Science and Logistics Society of INFORMS and served as the INFORMS student president at Iowa. Prior to his PhD, Michael worked with companies and nonprofits, including the Chicago Bears, UI Office of Sustainability and Integrated DNA Technologies, on consulting projects during his time in the Supply Chain & Analytics MBA program. He has been involved in education for the past decade and thoroughly enjoys teaching – before diving into academia, he was a K-8 Math and Spanish teacher in Omaha. Michael is beginning post-doctoral research with Dr. Mark Daskin and Ford Motor Company on supply chain and demand uncertainty and is looking forward to meeting everyone in the U-M IOE community.

]]>
Workshop / Seminar Thu, 24 Sep 2020 09:26:33 -0400 2020-10-01T15:00:00-04:00 2020-10-01T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Michael Redmond
SEMINAR: "Measuring and Mitigating Challenges for Future Human Spaceflight Missions" — Allison Anderson (October 8, 2020 3:00pm) https://events.umich.edu/event/76873 76873-19772611@events.umich.edu Event Begins: Thursday, October 8, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Measuring and Mitigating Challenges for Future Human Spaceflight Missions

Abstract:
The future of human spaceflight will send people away from the Earth for longer durations to explore the surface of the moon or Mars. The challenges associated with missions of this magnitude will require advances in technology to resolve these issues in early stages of design. Improved ways to evaluate habitat design, human factors, and perform ergonomics evaluation of spacecraft are needed. These missions will require increased crew autonomy and associated decision support. Additional countermeasures are needed to maintain human performance in operational, isolated, confined environments. These missions will also require novel spacesuits that minimized restricted mobility and injuries. This talk will discuss my research to measure and mitigate these issues. This research, while focused on individuals in extreme environments also has direct implications for patient populations here on Earth.

Bio:
Dr. Anderson graduated in 2007 with a B.S. in Astronautics Engineering from the University of Southern California with a minor in Astronomy. She received an M.S. in Aerospace Engineering and an M.S. in Technology Policy in 2011 from the Massachusetts Institute of Technology (MIT), and a Ph.D. in Aerospace Biomedical Engineering in 2014 from MIT. She received a postdoctoral fellowship from the National Space Biomedical Research Institute to work at Dartmouth Hitchcock Medical Center studying human space physiology. She is currently an Assistant Professor at the University of Colorado – Boulder Smead Department of Aerospace Engineering Sciences and an Adjunct Professor in Integrative Physiology. Her work focuses on aerospace biomedical engineering, spacesuit design, wearable sensors, spacecraft habitat design, alternative reality technologies, and human physiology in extreme environments. Specifically, her work is directed toward enabling a human mission to Mars.

]]>
Workshop / Seminar Thu, 24 Sep 2020 09:26:12 -0400 2020-10-08T15:00:00-04:00 2020-10-08T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Allison Anderson
SEMINAR: "Data-Driven Sample-Average Approximation for Stochastic Optimization with Covariate Information" — Jim Luedtke (October 15, 2020 3:00pm) https://events.umich.edu/event/76640 76640-19733033@events.umich.edu Event Begins: Thursday, October 15, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Data-Driven Sample-Average Approximation for Stochastic Optimization with Covariate Information

Abstract:
We consider optimization models for decision-making in which parameters within the optimization model are uncertain, but predictions of these parameters can be made using available covariate information. We consider a data-driven setting in which we have observations of the uncertain parameters together with concurrently-observed covariates. Given a new covariate observation, the goal is to choose a decision that minimizes the expected cost conditioned on this observation. We investigate a data-driven framework in which the outputs from a machine learning prediction model are directly used to define a stochastic programming sample average approximation (SAA). The framework is flexible and accommodates parametric, nonparametric, and semiparametric regression techniques. The basic version of this framework is not new, but we are the first to analyze the procedure and derive conditions on the data generation process, the prediction model, and the stochastic program under which solutions of these data-driven SAAs are consistent and asymptotically optimal. We also derive convergence rates and finite sample guarantees. We also propose new variations that use out-of-sample residuals of leave-one-out prediction models for scenario generation. Computational experiments validate our theoretical results, demonstrate the potential advantages of our data-driven formulations over existing approaches (even when the prediction model is misspecified), and illustrate the benefits of our new variants in the limited data regime.

Bio:
Jim Luedtke is a Professor and Associate Chair for Graduate Studies in the department of Industrial and Systems Engineering at the University of Wisconsin-Madison. Luedtke earned his PhD at Georgia Tech and did postdoctoral work at the IBM T.J. Watson Research Center. Luedtke’s research is focused on methods for solving stochastic and mixed-integer optimization problems, as well as applications of such models. Luedtke is a recipient of an NSF CAREER award, was a finalist in the INFORMS JFIG Best Paper competition, and was awarded the INFORMS Optimization Society Prize for Young Researchers. Luedtke serves on the editorial boards of the journals SIAM Journal on Optimization and Mathematical Programming Computation, is the current secretary of the SIAM Activity Group in Optimization, and is chair of the Mathematical Optimization Society Publications Committee.

]]>
Workshop / Seminar Thu, 24 Sep 2020 09:26:54 -0400 2020-10-15T15:00:00-04:00 2020-10-15T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Departmental Seminar (899)
SEMINAR: "Information-theoretic Generalization Bounds for Noisy, Iterative Learning Algorithms" — Daniel Roy (October 22, 2020 3:00pm) https://events.umich.edu/event/78573 78573-20066114@events.umich.edu Event Begins: Thursday, October 22, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Information-theoretic Generalization Bounds for Noisy, Iterative Learning Algorithms

Abstract:
Deep learning approaches dominate in many application areas. Our understanding of generalization (relating empirical performance to future expected performance) is however lacking. In some applications, standard algorithms like stochastic gradient descent (SGD) reliably return solutions with low test error. In other applications, these same algorithms rapidly overfit. There is, as yet, no satisfying theory explaining what conditions are required for these common algorithms to work in practice. In this talk, I will discuss standard approaches to explaining generalization in deep learning using tools from statistical learning theory, and present some of the barriers these approaches face to explaining deep learning. I will then discuss my group's recent work (NeurIPS 2019, 2020) on information-theoretic approaches to understanding generalization of noisy, iterative learning algorithms, such as Stochastic Gradient Langevin Dynamics, a noisy version of SGD.

Bio:
Daniel Roy is an Associate Professor in the Department of Statistical Sciences at the University of Toronto, with cross appointments in Computer Science and Electrical and Computer Engineering. He is also a CIFAR Canada AI Chair at the Vector Institute. Roy's research spans machine learning, mathematical statistics, and theoretical computer science. Roy is a recipient of an NSERC Discovery Accelerator Supplement, Tri-agency New Frontiers in Research grant, Ontario Early Research Award, and a Google Faculty Research Award. Prior to joining Toronto, Roy was a Research Fellow of Emmanuel College and Newton International Fellow of the Royal Society and Royal Academy of Engineering, hosted by the University of Cambridge. Roy completed his doctorate in Computer Science at the Massachusetts Institute of Technology, where his dissertation was awarded the MIT EECS Sprowls Award, given to the top dissertation in computer science in that year.

]]>
Workshop / Seminar Thu, 15 Oct 2020 10:29:01 -0400 2020-10-22T15:00:00-04:00 2020-10-22T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Daniel Roy
SEMINAR: "COVID-19 Forecasting: Three Cheers for Simple Models" — Eric Bickel (October 29, 2020 3:00pm) https://events.umich.edu/event/76755 76755-19743031@events.umich.edu Event Begins: Thursday, October 29, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
COVID-19 Forecasting: Three Cheers for Simple Models

Abstract:
Over the last six months we have witnessed policymakers grappling with how to respond to the spread of COVID-19 across the globe. In the United States, policymakers at local, state, and federal levels have faced difficult decisions regarding the degree to which citizens should interact with each other, how much of the economy should be curtailed, and how to allocate scarce testing and hospital resources. These decisions have been informed and guided by a set of epidemiological models.

In this talk, we analyze the performance of the models used to forecast the spread of COVID-19 and relate differences in performance to differing modeling approaches and structures. For example, some COVID-19 models are “bottom-up” and model the interactions between individuals in detail. While other models are “top-down” and attempt to capture the high-level dynamics of the spread. Some models include uncertainty, while others are deterministic. Certain models are designed to inform policy decisions, while others are meant to provide forecasts.

We compare the performance of these models to a simple (one-parameter) model that we have used to forecast the spread of COVID-19 at the national, state, and local level. Surely large models with dozens of parameters, backed by a team of experts, should outperform a simple model that has one input and runs in Excel. As we discuss, a few COVID-19 models do achieve this level of success.

We will discuss this apparent paradox and the implications for decision analysis.

Bio:
Eric Bickel is a professor and director of both the Operations Research & Industrial Engineering and Engineering Management programs at The University of Texas at Austin. Eric holds a courtesy appointment in the Department of Information, Risk, and Operations Management in the McCombs School of Business and directs the Center for Engineering and Decision Analytics (CEDA).

His research interests include the theory and practice of decision analysis and its application to corporate strategy, public policy, and sports. His work has been featured in The Wall Street Journal, The New York Times, The Financial Times, and Sports Illustrated. In addition, Professor Bickel and his research are featured in the documentary Cool It!. His research into climate engineering was named as the top approach to address climate change by a panel of economists, including three Nobel Laureates. He has also been a guest on the MLB Network show Clubhouse Confidential.

Eric joined Strategic Decisions Group in 1995, where he remains a director and partner. He has practiced decision analysis for 25 years. He consults around the world in a range of industries, including oil and gas, electricity generation/transmission/delivery, energy trading and marketing, commodity and specialty chemicals, life sciences, financial services, and metals and mining.

He is Past-President of the Decision Analysis Society.

Eric holds both M.S. and Ph.D. degrees from the Department of Engineering-Economic Systems at Stanford University and a B.S. in mechanical engineering with a minor in economics from New Mexico State University.

Eric claims to be the only decision analyst listed in Hollywood's Internet Movie Database (imdb.me/jericbickel).

]]>
Workshop / Seminar Thu, 24 Sep 2020 09:28:06 -0400 2020-10-29T15:00:00-04:00 2020-10-29T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Departmental Seminar (899)
SEMINAR: "Sparse Estimation: Closing the Gap Between L0 and L1 Models" — Alper Atamturk (November 5, 2020 3:00pm) https://events.umich.edu/event/76453 76453-19717149@events.umich.edu Event Begins: Thursday, November 5, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Sparse Estimation: Closing the Gap Between L0 and L1 Models

Abstract:
Sparse statistical estimators are increasingly prevalent due to their ease of interpretability and superior out-of-sample performance. However, sparse estimation problems with an L0 constraint, restricting the support of the estimators, are challenging (typically NP-hard, but not always) non-convex optimization problems. Consequently, academics and practitioners commonly turn to convex L1 proxies, such as Lasso and its variants, as a remedy. Although the L1 models are solved fast, they may lead to biased and/or dense estimators and require substantial cross-validation for calibration.

In this talk, we focus on two estimation problems: i) sparse regression and ii) sparse and smooth signal recovery. The first one is known to be NP-hard; we show that the second one is equivalent to a submodular minimization problem and, hence, is polynomially solvable. For both problems, we derive a sequence of strong convex relaxations. These relaxations are based on the ideal (convex-hull) formulations for rank-one/pairwise quadratic terms with indicator variables. The new relaxations can be formulated as conic quadratic or semidefinite optimization problems in an extended space; they are stronger and more general than the state-of-the-art models with the reverse Huber penalty and the minimax concave penalty functions. Furthermore, the proposed rank-one strengthening can be interpreted as a non-separable, non-convex, unbiased sparsity-inducing regularizer, which dynamically adjusts its penalty according to the shape of the estimation error function without inducing bias for the sparse solutions. Computational experiments with benchmark datasets show that the proposed conic formulations are solved fast and result in near-optimal estimators for non-convex L0-problems. Moreover, the resulting estimators also outperform L1 approaches from a statistical perspective, achieving high prediction accuracy and good interpretability.

This talk is based on the following papers with Andres Gomez & Shaoning Han:

https://atamturk.ieor.berkeley.edu/pubs/rank-one.pdf
https://atamturk.ieor.berkeley.edu/pubs/screening.pdf
https://atamturk.ieor.berkeley.edu/pubs/signal-estimation.pdf

]]>
Workshop / Seminar Fri, 23 Oct 2020 10:38:58 -0400 2020-11-05T15:00:00-05:00 2020-11-05T16:00:00-05:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Departmental Seminar (899)
SEMINAR: "Coordinated Delivery to Shopping Malls with Limited Docking Capacity" — Lei Zhao (November 19, 2020 10:00am) https://events.umich.edu/event/75964 75964-19629764@events.umich.edu Event Begins: Thursday, November 19, 2020 10:00am
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Coordinated Delivery to Shopping Malls with Limited Docking Capacity

Abstract:
Shopping malls are densely located in densely populated cities such as Singapore and Hong Kong. Tenants in these shopping malls generate a large number of freight orders to their contracted logistics service providers, who then independently plan their own delivery schedules. These uncoordinated deliveries and the limited docking capacity often jointly cause congestion at the shopping malls. We study a coordination strategy in which a delivery coordination platform centrally schedules vehicle routes for multiple logistics service providers, and simultaneously reserves the dock time slot for each order delivery. Vehicle routing and dock scheduling decisions are made jointly against the backdrop of travel time and service time uncertainty. We model this problem as a two-stage stochastic mixed integer program, develop an Adaptive Large Neighborhood Search algorithm that approximates the second stage recourse function using various sample sizes, and examine the associated in-sample and out-of-sample stability. Our numerical study on a testbed of instances based on real data in Singapore demonstrates the value of coordination and the value of stochastic solutions.

Bio:
Dr. Lei Zhao is an associate professor in the Department of Industrial Engineering at Tsinghua University. His research focuses on computational stochastic optimization methodologies (stochastic programming, approximate dynamic programming, simulation optimization) and their applications in logistics and transportation management (esp. urban delivery in megacities), supply chain risk management, and medical decision making. Dr. Zhao’s research has been funded by the National Natural Science Foundation of China (NSFC) and Ministry of Science and Technology of China (MoST) as well as industry collaborators such as Sinoair, Sinopec, China Tobacco, COSCO Shipping Technology/COSCONET, Mitsubishi Heavy Industries, General Mills, IBM, etc. He has publications in Annals of Operations Research, Computers & Operations Research, European Journal of Operational Research, Manufacturing & Service Operations Management, OR Spectrum, Transportation Research Part B, C, & E, and Transportation Science, etc.

]]>
Workshop / Seminar Tue, 17 Nov 2020 10:05:00 -0500 2020-11-19T10:00:00-05:00 2020-11-19T11:00:00-05:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Lei Zhao
SEMINAR: "Large-scale Inference of Time-varying Markov Random Fields: Bridging the Gap Between Statistical and Computational Efficiencies" — Salar Fattahi (December 3, 2020 3:00pm) https://events.umich.edu/event/75965 75965-19629765@events.umich.edu Event Begins: Thursday, December 3, 2020 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

This event will be a joint seminar with the MICDE.

Title:
Large-scale Inference of Time-varying Markov Random Fields: Bridging the Gap Between Statistical and Computational Efficiencies

Abstract:
Contemporary systems are comprised of a massive number of interconnected components that interact according to a hierarchy of complex, dynamic, and unknown topologies. For example, with billions of neurons and hundreds of thousands of voxels, the human brain is considered as one of the most complex physiological networks, whose structure remains as a long-standing mystery. As another example, the emergence of self-driving cars has only accentuated the need for the development of real-time and reliable methods for detecting moving objects, whose temporal locations are captured through a dynamically-evolving 3D network. Nonetheless, the vast amounts of parameters to be estimated, caused both by the large number of components and the time-varying nature of the systems, are currently the major bottlenecks in our ability to successfully solve such inference problems.

The temporal behavior of today's interconnected systems can be captured via time-varying Markov random fields (MRF). A popular approach to achieve this goal is based on the so-called maximum-likelihood estimation (MLE): to find a probabilistic graphical model, based on which the observed data is most probable to occur. The MLE-based methods suffer from several fundamental drawbacks which render them impractical in realistic settings. First, they often suffer from notoriously high computational cost in the massive problems, where the number of variables to be inferred is in the order of millions, or more. Second, they fail to efficiently incorporate prior structural information into their estimation procedure. With the goal of bridging this knowledge gap, the aim of this work is to revisit the standard MLE as the “Holy Grail” of the inference methods for graphical models, and precisely pinpoint and remedy the scenarios where it fails. A recurring theme in our proposed approach is a class of efficiently-solvable mixed-integer optimization problems that is used in lieu of the regularized MLE for the inference of time-varying MRFs. Our proposed optimization problems enjoy strong statistical and computational guarantees, while being amenable to a wide class of graphical models with different side information, such as sparsity, smoothness, etc.

Bio:
Salar Fattahi is an Assistant Professor in the Department of Industrial and Operations Engineering at the University of Michigan. He received his M.S. and Ph.D. degrees in Industrial Engineering and Operations Research from UC Berkeley. He received a M.S. degree from Columbia University, and a B.S. degree from Sharif University of Technology, Iran, both in Electrical Engineering. Salar’s research lies at the intersection of optimization, data analytics, and control theory. He was the recipient of several awards, including the 2020 INFORMS ENRE Best Student Paper Award, 2018 INFORMS Data Mining Best Paper Award and 2020 Power & Energy Society General Meeting Best-of-the-Best Paper Award. He was also a finalist for the 2018 American Control Conference Best Paper Award.

]]>
Workshop / Seminar Tue, 17 Nov 2020 10:14:22 -0500 2020-12-03T15:00:00-05:00 2020-12-03T16:00:00-05:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Salar Fattahi
SEMINAR: "Importance Sampling with Stochastic Computer Models: From Theory to Practice" — Eunshin Byon (March 11, 2021 3:00pm) https://events.umich.edu/event/82612 82612-21145764@events.umich.edu Event Begins: Thursday, March 11, 2021 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Importance Sampling with Stochastic Computer Models: From Theory to Practice

Abstract:
Importance sampling has been widely used to improve the efficiency of deterministic computer simulations where the simulation output is uniquely determined, given a fixed input. To represent complex system behavior more realistically, however, stochastic computer models are gaining popularity. Unlike deterministic computer simulations, stochastic simulations produce different outputs even at the same input. This extra degree of stochasticity presents a challenge in analyzing engineering system performance. Our study tackles this challenge by addressing two problems. First, we derive the optimal importance sampling density and allocation procedure that minimize the variance of an estimator. Second, we present a non-parametric approach to approximate the optimal importance sampling density with a multivariate input vector when each factor’s contribution is different. The application of our method to a computationally intensive, aeroelastic wind turbine simulator demonstrates the benefits of the proposed approaches.

Bio:
Eunshin Byon is an Associate Professor in the Department of Industrial and Operations Engineering at the University of Michigan, Ann Arbor, USA. She received her Ph.D. degree in the Industrial and Systems Engineering from the Texas A&M University, College Station, USA in 2010. Dr. Byon’s research interests include data analytics, quality and reliability engineering, system informatics and uncertainty quantification. She has received several Best Paper Awards including the Best Applications Paper Award from IISE Transactions on Quality& Reliability Engineering. Dr. Byon has served the Quality, Statistics, and Reliability (QSR) subdivision of INFORMS as a chair-elect and chair in 2019-2020. She is a member of IIE, INFORMS and IEEE.

]]>
Workshop / Seminar Fri, 05 Mar 2021 10:53:05 -0500 2021-03-11T15:00:00-05:00 2021-03-11T16:00:00-05:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Eunshin Byon
SEMINAR: "Optimizing the First Response to Sepsis: An Electronic Health Record-based Markov Decision Process Model for Personalizing Acute Care for Deteriorating Patients" — Julie Simmons Ivy (March 18, 2021 3:00pm) https://events.umich.edu/event/82909 82909-21217313@events.umich.edu Event Begins: Thursday, March 18, 2021 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Optimizing the First Response to Sepsis: An Electronic Health Record-based Markov Decision Process Model for Personalizing Acute Care for Deteriorating Patients

Abstract:
Sepsis is considered a medical emergency where delays in initial treatment are associated with increased morbidity and mortality. It is a life-threatening organ dysfunction caused by a dysregulated host response to infection. Sepsis affects more than 1.7 million Americans each year, causing approximately 270,000 deaths annually. One in three hospitalized patient deaths are associated with sepsis. In 2019, the total cost of sepsis care for inpatient admission and skilled nursing facility admission was estimated at more than $62 billion. Sepsis is a significant healthcare challenge, where the lack of a gold standard for diagnosis causes inconsistencies in categorizing sepsis phenotypes and accurately capturing patients’ trajectories, which evolve stochastically over time. This makes treatment decision making and early intervention difficult. We integrate electronic health record (EHR) data with clinical expertise to develop a continuous-time Markov decision process model of the natural history of sepsis. We use this model to better understand the stochastic nature of patients’ health trajectories and determine the optimal treatment policy to minimize mortality and morbidity. Specifically, the optimal health states for first anti-infective and first fluid are identified. We formulate this as a stopping problem in which the patient leaves the system when he or she receives the first treatment (intervention) and receives a lump sum reward. Our objective is to find the optimal first intervention for health states to minimize expected mortality and morbidity. We explore the effect of the complex trade-offs associated with the intervention costs and patient disposition costs which are subjective and difficult to estimate. Our model captures the natural progression along sepsis trajectory using a clinically defined treatment delayed population. The model translates observations of patient health as defined by vitals and laboratory results recorded during hospitalization in the EHR to capture the complex evolution of sepsis within a patient population. This framework provides key insights into sepsis patients’ stochastic trajectories and informs clinical decision making associated with caring for these patients as their health dynamically evolves.

Bio:
Julie Simmons Ivy is a Professor in the Edward P. Fitts Department of Industrial and Systems Engineering and Fitts Faculty Fellow in Health Systems Engineering. She previously spent several years on the faculty of the Stephen M. Ross School of Business at the University of Michigan. She received her B.S. and Ph.D. in Industrial and Operations Engineering at the University of Michigan. She also received her M.S. in Industrial and Systems Engineering with a focus on Operations Research at Georgia Tech. She is a President of the Health Systems Engineering Alliance (HSEA) Board of Directors. She is an active member of the Institute of Operations Research and Management Science (INFORMS), Dr. Ivy served as the 2007 Chair (President) of the INFORMS Health Applications Society and the 2012 – 13 President for the INFORMS Minority Issues Forum. Her research interests are mathematical modeling of stochastic dynamic systems with emphasis on statistics and decision analysis as applied to health care, public health, and humanitarian logistics. This research has made an impact on how researchers and practitioners address complex societal issues, such as health disparities, public health preparedness, hunger relief, student performance, and personalized medical decision-making and has been funded by AHRQ, CDC, NSF, Clinton Health Access Initiative, and the UNC Cancer Center.

]]>
Workshop / Seminar Wed, 10 Mar 2021 08:58:09 -0500 2021-03-18T15:00:00-04:00 2021-03-18T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Julie Simmons Ivy
SEMINAR: "Modeling to Promote an Efficient, Effective and Equitable Response to the Covid-19 Pandemic" — Julie Swann (March 25, 2021 3:00pm) https://events.umich.edu/event/83187 83187-21290773@events.umich.edu Event Begins: Thursday, March 25, 2021 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Modeling to Promote an Efficient, Effective and Equitable Response to the Covid-19 Pandemic

Abstract:
Planning and response to the Covid-19 pandemic is complex but can be informed by analytics and mathematical modeling along with knowledge of public health and supply chain contexts. This talk will summarize disease modeling embedded in a Covid-19 network simulation, highlighting recent results analyzing pharmaceutical and other interventions as well as potential future scenarios. The talk will provide an overview of how the public health system in the US allocates and distributes Covid-19 vaccine along with potential pitfalls and areas for improvement. The talk will discuss several areas where analytics and modeling are impacting efficiency, effectiveness, and equity.

Bio:
Julie Swann is the department head and A. Doug Allison Distinguished Professor of the Fitts Department of Industrial and Systems Engineering. She is an affiliate faculty in the Joint Department of Biomedical Engineering at both NC State and the University of North Carolina at Chapel Hill. Before joining NC State, Swann was the Harold R. and Mary Anne Nash Professor in the Stewart School of Industrial and Systems Engineering at the Georgia Institute of Technology. There she co-founded and co-directed the Center for Health and Humanitarian Systems (CHHS), one of the first interdisciplinary research centers on the Georgia Tech campus. Starting with her work with CHHS, Swann has conducted research, outreach and education to improve how health and humanitarian systems operate worldwide.

]]>
Workshop / Seminar Fri, 19 Mar 2021 13:49:51 -0400 2021-03-25T15:00:00-04:00 2021-03-25T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Julie Swann
SEMINAR: "Informing Anti-Human Trafficking Efforts with Operations Research Models" — Kayse Maass (April 1, 2021 3:00pm) https://events.umich.edu/event/82843 82843-21201314@events.umich.edu Event Begins: Thursday, April 1, 2021 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Informing Anti-Human Trafficking Efforts with Operations Research Models

Abstract:
Human trafficking is a prevalent and malicious global human rights issue, with an estimated 24 million victims currently being exploited worldwide. A major challenge to its disruption is the fact that human trafficking is a complex system interwoven with other illegal and legal networks, both cyber and physical. Efforts to disrupt human trafficking must understand these complexities and the ways in which a disruption to one portion of the network affects other network components. As such, operations research models are uniquely positioned to address the challenges facing anti-human trafficking efforts. This presentation will discuss ongoing interdisciplinary anti-human trafficking efforts focusing on prevention, network disruption, and survivor empowerment. Specifically, we will discuss 1) the adaptions to current network interdiction models that are necessary for adequately representing human trafficking contexts and 2) a budget-constrained optimization model that maximizes the societal value of locating additional shelters for human trafficking survivors.

Bio:
Dr. Kayse Lee Maass is an Assistant Professor of Industrial Engineering and leads the Operations Research and Social Justice Lab at Northeastern University. Her research focuses on the application of operations research methodology to social justice, access, and equity issues within human trafficking, mental health, housing, and supply chain contexts. This includes determining how to most effectively allocate limited resources to disrupt human trafficking networks, increase access to services for survivors, and assess the efficacy of coordination among anti-human trafficking stakeholders. Dr. Maass’s research is supported by multiple federal grants, centers interdisciplinary survivor-informed expertise, and has informed local, national, and international policy and operational decisions.
Dr. Maass earned a PhD in Industrial and Operations Engineering (IOE) from the University of Michigan and completed her postdoctoral studies in the Department of Health Sciences Research at the Mayo Clinic. She is a recipient of multiple awards, including: the INFORMS Judith Liebman Award, Industrial Engineering Professor of the Year at Northeastern University, NSF Graduate Research Fellowship Program Award, and the INFORMS Section on Location Analysis Dissertation Award-Runner Up. She was also named a ‘Rising Star’ among INFORMS’ Powerful, Pragmatic Pioneers. Dr. Maass currently serves on the INFORMS Subdivision Council, as INFORMS Section on Location Analysis Secretary, and is part of the U.N. University Delta 8.7 Markets Working Group.
Bass is a fellow of the Human Factors and Ergonomics Society and a senior member of the IEEE and of the American Institute of Aeronautics and Astronautics. Dr. Bass is the incoming Secretary-Treasurer Elect of the Human Factors and Ergonomics Society. She is a member of the editorial board for three journals: Human Factors, IIE Transaction on Occupational Ergonomics and Human Factors and the Journal of Cognitive Engineering and Decision Making. She was the inaugural editor of the IEEE Trans. on Human-Machine Systems. She is a peer reviewer for several international research programs.

]]>
Workshop / Seminar Mon, 08 Mar 2021 09:18:52 -0500 2021-04-01T15:00:00-04:00 2021-04-01T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Kayse Maass
SEMINAR: "Supporting medication reconciliation and medication self-management: the implication of home health quality reporting requirements on the home care admission visit" — Ellen Bass (April 8, 2021 3:00pm) https://events.umich.edu/event/82700 82700-21161634@events.umich.edu Event Begins: Thursday, April 8, 2021 3:00pm
Location: Off Campus Location
Organized By: U-M Industrial & Operations Engineering

The Departmental Seminar Series is open to all. U-M Industrial and Operations Engineering graduate students and faculty are especially encouraged to attend.

Title:
Supporting medication reconciliation and medication self-management: the implication of home health quality reporting requirements on the home care admission visit

Abstract:
In the United States, the landscape for the operations and evaluation of Medicare-certified home health agencies has changed radically in the last five years. In January 2016, the Center for Medicare & Medicaid Innovation Center launched the Home Health Value Based Purchasing Model (HHVBPM) and in November 2018, CMS finalized a case-mix classification model that went into effect January 1, 2020. The timeframe of home health payments changed from a 60-day episode to a 30-day period. To evaluate the agencies, the model uses data from several sources. The inclusion of Outcome and Assessment Information Set (OASIS) dataset derived from the patient home care episodes coupled with the shortening of the home care episode period place a burden on the admission visit. Systems engineering research can help to address the associated data collection and documentation burden. Given that home care and other post-acute care settings were omitted from Meaningful Use developments, their progress in supporting smooth information transfer and applications of decision support and data science lag behind acute care. Thus research can identify whether some data could be acquired as part of the referral into home care. Finally research is required to ensure that the quality and outcome measures are differentiating the agencies in ways that improve patient care. This talk will discuss a four-year multidisciplinary collaborative research project addressing standards for health information technology to support the homecare admission process. It will address the characterization of information requirements, decision-making, and workflow for admitting nurses based on focus groups, observations, and document review of 3 agencies (serving rural, suburban, urban populations) using 3 different HIT systems. The analysis will focus on three critical clinical decisions (medication self-management capability, problems to put on the care plan, next visit timing and frequency of future visits).

Bio:
Ellen J. Bass is Interim Associate Dean for Research and Professor in the Department of Information Science in the Drexel University’s College of Computing and Informatics. She is a Professor and Chair of the Department of Health Systems and Sciences Research in the College of Nursing and Health Professions. She also holds affiliate status in Drexel University’s School of Biomedical Engineering, Science and Health Systems. She is also Adjunct Professor of Anesthesiology and Critical Care at the University of Pennsylvania’s School of Medicine.

Bass has over 30 years of human-centered systems engineering research and design experience in multiple domains. The focus of her research is to develop theories of human performance, quantitative modeling methodologies, measures, and associated experimental designs that can be used to evaluate human-automation interaction and human-human coordination in the context of total system performance. She has published over 150 peer-reviewed publications. Her research program is currently funded by the FAA, NIH, PCORI, and the VA.

Bass is a fellow of the Human Factors and Ergonomics Society and a senior member of the IEEE and of the American Institute of Aeronautics and Astronautics. Dr. Bass is the incoming Secretary-Treasurer Elect of the Human Factors and Ergonomics Society. She is a member of the editorial board for three journals: Human Factors, IIE Transaction on Occupational Ergonomics and Human Factors and the Journal of Cognitive Engineering and Decision Making. She was the inaugural editor of the IEEE Trans. on Human-Machine Systems. She is a peer reviewer for several international research programs.

Bass holds a Ph.D. in Industrial and Systems Engineering from the Georgia Institute of Technology, an M.S. in Advanced Technology from the State University of New York at Binghamton, a B.S.Eng. in Bioengineering from the University of Pennsylvania, and a B.S.Econ. in Finance from the University of Pennsylvania.

]]>
Workshop / Seminar Fri, 05 Mar 2021 10:19:26 -0500 2021-04-08T15:00:00-04:00 2021-04-08T16:00:00-04:00 Off Campus Location U-M Industrial & Operations Engineering Workshop / Seminar Ellen J Bass