Title: Algorithmic Leveraging Predictions for Online Resource Allocation and Faster Optimization
Abstract: This talk will discuss a model for augmenting discrete optimization algorithms with machine learned predictions to improve algorithm performance. First the talk will discuss online resource allocation using predictions. Predictions will be leveraged to go beyond the worst case lower bounds in both the regret and competitive analysis frameworks. Then the talk will discuss how to speed up optimization algorithms via machine learned warm start.
Bio: Ben Moseley is the Carnegie-Bosch Associate Professor of Operations Research at Carnegie Mellon University (CMU) and is a consulting scientist at Relational AI. He obtained his Ph.D. from the University of Illinois. During his career, his papers have won best paper or best student paper awards at IPDPS (2015), SPAA (2013) and SODA (2010). His papers have been recognized as top publications with honors such as Oral Presentations at NuerIPS (2021, 2017) and NeurIPS Spotlight Papers (2023, 2018). He has served as Area Chair for ICML, ICLR, and NeurIPS every year since 2020 and has been on many program committees including SODA (2022, 2018), ESA (2017), SPAA (2024, 2022, 2021, 2016). He was an Associate Editor for IEEE Transactions on Knowledge and Data Engineering (TKDE) from 2018-2022 and has served as Associate Editor of Operations Research Letters since 2017. He has won the NSF CAREER Award, two Google Research Faculty Awards, a Yahoo ACE Award, and an Infor faculty award. He was selected as a Top 50 Undergraduate Professor by Poets and Quants. His research interests broadly include algorithms, machine learning, and discrete optimization. He is currently excited about how to robustly incorporate machine learning into decision-making processes.
