Organizer

Aadirupa Saha is a postdoctoral researcher at Microsoft Research (MSR) in New York City. Earlier she was a Ph.D. student at Indian Institute of Science (IISc) Bangalore. Her research interests broadly lie in the areas of Bandits and Reinforcement Learning, Optimization, Learning theory, and Differential Privacy. Her current research focuses on developing large-scale robust algorithms for sequential decision-making under restricted feedback, especially where the loss/reward functions are ill-defined---some potential problem settings include learning from preference feedback or partial rankings, proxy rewards, multiobjective optimization, etc. Some of her other recent ventures also include handling non-stationarity, analyzing tightness guarantees of algorithms, multiplayer games, online optimization. Broadly, she is fascinated by the scope of closing the gap between Human vs Machine intelligence towards solving real-world problems from a theoretical viewpoint.

Website: https://aadirupa.github.io/ Email: aadirupa.saha@gmail.com