{
    "141373-21888712":
    {
        "datetime_modified":"20260407T124520",
        "datetime_start":"20261007T160000",
        "datetime_end":"20261007T170000",
        "has_end_time":1,
        "date_start":"2026-10-07",
        "date_end":"2026-10-07",
        "time_start":"16:00:00",
        "time_end":"17:00:00",
        "time_zone":"America\/Detroit",
        "event_title":"Robust and Risk-Sensitive Acceleration in Gradient Methods",
        "occurrence_title":"",
        "combined_title":"Robust and Risk-Sensitive Acceleration in Gradient Methods: Mert Gurbuzbalaban, Rutgers",
        "event_subtitle":"Mert Gurbuzbalaban, Rutgers",
        "event_type":"Workshop \/ Seminar",
        "event_type_id":"21",
        "description":"First-order methods such as gradient descent (GD) are foundational in optimization. In unconstrained problems with exact gradients, momentum-based methods\u2014most notably Nesterov\u2019s accelerated gradient descent (AGD) and Polyak\u2019s heavy-ball (HB) method\u2014achieve faster convergence by improving dependence on the condition number. However, this acceleration comes at a cost: momentum amplifies gradient noise, making these methods less robust than GD under standard parameter choices and requiring more accurate gradient estimates to attain comparable accuracy. Similar challenges arise in convex and nonconvex min\u2013max optimization.\nMotivated by applications in machine learning, this talk studies unconstrained and min\u2013max optimization under deterministic, unbiased stochastic, and biased stochastic gradient noise. I will present new algorithms that achieve optimal robustness against different noise types, using control-theoretic tools such as the H_2\u200b norm, the H_\u221e\u200b norm, and the risk-sensitivity index, together with coherent risk measures. I will also discuss worst-case noise constructions and high-probability convergence guarantees. This perspective builds a bridge between optimization and robust control theory and enables the design of noise-robust and risk-sensitive accelerated methods.\nRepresentative Publications:\nM. G\u00fcrb\u00fczbalaban, Y. Syed, N. S. Aybat, Accelerated gradient methods with biased gradient estimates: Risk sensitivity, high-probability guarantees, and large deviation bounds, Journal of Nonlinear and Variational Analysis, 2026 (Special Issue). https:\/\/jnva.biemdas.com\/archives\/2927\nM. G\u00fcrb\u00fczbalaban, Robustly Stable Accelerated Momentum Methods with a Near-Optimal L_2\u200b Gain and H_\u221e\u200b Performance, Mathematics of Operations Research, 2025.\nhttps:\/\/pubsonline.informs.org\/doi\/abs\/10.1287\/moor.2023.0321\nB. Can and M. G\u00fcrb\u00fczbalaban, Entropic risk-averse generalized momentum methods, Optimization Methods and Software, 2025. https:\/\/www.tandfonline.com\/doi\/abs\/10.1080\/10556788.2025.2549356",
        "occurrence_notes":null,
                "guid":"141373-21888712@events.umich.edu",
        "permalink":"http:\/\/events.umich.edu\/event\/141373",
        "building_id":"1000166",
        "building_name":"East Hall",
        "campus_maps_id":"53",
        "room":"1360",
        "location_name":"East Hall",
        "has_livestream":0,
        "cost":"",
        "tags":["Mathematics"],
        "website":"",
        "sponsors":[
             {
                "group_name":"Financial\/Actuarial Mathematics Seminar - Department of Mathematics",
                "group_id":"4890",
                "website":""                }                    ],
        "image_url":"",
        "styled_images":{
                                        "event_thumb":"",
                                            "event_large":"",
                                            "event_large_2x":"",
                                            "event_large_lightbox":"",
                                            "group_thumb":"",
                                            "group_thumb_square":"",
                                            "group_large":"",
                                            "group_large_lightbox":"",
                                            "event_large_crop":"",
                                            "event_list":"",
                                            "event_list_2x":"",
                                            "event_grid":"",
                                            "event_grid_2x":"",
                                            "event_feature_large":"",
                                            "event_feature_thumb":""                    },
        "occurrence_count":1,
        "first_occurrence":21888712
    }    ,    "148617-21904532":
    {
        "datetime_modified":"20260608T221120",
        "datetime_start":"20261028T160000",
        "datetime_end":"20261028T170000",
        "has_end_time":1,
        "date_start":"2026-10-28",
        "date_end":"2026-10-28",
        "time_start":"16:00:00",
        "time_end":"17:00:00",
        "time_zone":"America\/Detroit",
        "event_title":"TBA",
        "occurrence_title":"",
        "combined_title":"TBA: Zhenjie Ren, University of Evry",
        "event_subtitle":"Zhenjie Ren, University of Evry",
        "event_type":"Workshop \/ Seminar",
        "event_type_id":"21",
        "description":"TBA",
        "occurrence_notes":null,
                "guid":"148617-21904532@events.umich.edu",
        "permalink":"http:\/\/events.umich.edu\/event\/148617",
        "building_id":"1000166",
        "building_name":"East Hall",
        "campus_maps_id":"53",
        "room":"1360",
        "location_name":"East Hall",
        "has_livestream":0,
        "cost":"",
        "tags":["Mathematics"],
        "website":"",
        "sponsors":[
             {
                "group_name":"Financial\/Actuarial Mathematics Seminar - Department of Mathematics",
                "group_id":"4890",
                "website":""                }                    ],
        "image_url":"",
        "styled_images":{
                                        "event_thumb":"",
                                            "event_large":"",
                                            "event_large_2x":"",
                                            "event_large_lightbox":"",
                                            "group_thumb":"",
                                            "group_thumb_square":"",
                                            "group_large":"",
                                            "group_large_lightbox":"",
                                            "event_large_crop":"",
                                            "event_list":"",
                                            "event_list_2x":"",
                                            "event_grid":"",
                                            "event_grid_2x":"",
                                            "event_feature_large":"",
                                            "event_feature_thumb":""                    },
        "occurrence_count":1,
        "first_occurrence":21904532
    }    }