Michał Dereziński
Michał Dereziński is a postdoctoral researcher at UC Berkeley’s Foundations of Data Analysis Institute. Previously, he was a research fellow at the Simons Institute for the Theory of Computing. He obtained his PhD in Computer Science at UC Santa Cruz, advised by professor Manfred Warmuth. Michał’s recent work includes proposing efficient algorithms for determinantal point processes, and applying them to new settings in stochastic optimization and experimental design. More broadly, he is interested in using randomized algorithms to improve the performance and provide better theoretical understanding of methods in statistics, machine learning and optimization.
Mike Gartrell
Mike Gartrell is a senior researcher at the Criteo AI Lab in Paris, France. His recent research interests include modeling approaches for structured prediction and recommendation, including determinantal point processes, and he has published a number of papers on these topics. He is broadly interested in both theoretical and applied aspects of machine learning, including Bayesian probabilistic modeling and recommendation systems. Previously, he worked as a postdoctoral researcher at Microsoft in Herzliya, Israel. He received his PhD in 2014 in Computer Science from the University of Colorado Boulder.
Zelda Mariet
Zelda Mariet is a Research Scientist at Google Research, in Cambridge, MA. Her research interests focus on the theoretical aspects of machine learning, and particularly on subset-selection problems for model design. Recently, she has also been thinking about machine learning for biological sequence design. Zelda obtained her PhD at MIT in 2019, where she
studied the theory and application of negatively-dependent measures for machine learning model design and optimization, advised by Suvrit Sra. She received the 2018 Google PhD Fellowship in machine learning, and has published extensively on determinantal point processes and subset-selection tasks for recommender systems and experimental design.