Workshops

Fall 2020

Mathematics of Online Decision Making

Oct. 26 – Oct. 30, 2020

Return to event »

All talks are listed in Pacific Time (PDT).

Monday, October 26th, 2020
8:50 am – 9:00 am		Opening Remarks
9:00 am – 9:30 am		Online Multiserver Convex Chasing and Optimization Yuval Rabani (Hebrew University of Jerusalem)
9:30 am – 10:00 am		Multi-Task Optimal Experiment Design Steffen Grunewalder (Lancaster University)
10:00 am – 10:30 am		Selfish Robustness and Equilibria in Multi-Player Bandits Vianney Perchet (ENSAE & Criteo AI Lab)
10:30 am – 11:00 am		Discussion
11:00 am – 11:30 am		Break
11:30 am – 12:00 pm		Pure Exploration Problems Wouter Koolen (Centrum Wiskunde & Informatica)
12:00 pm – 12:30 pm		Gradient Descent-Ascent Provably Converges to Strict Local Minmax Equilibria with a Finite Timescale Separation Lillian Ratliff (University of Washington)
12:30 pm – 1:00 pm		Learning Outcomes in Queueing Systems Eva Tardos (Cornell)
1:00 pm – 1:30 pm		Discussion

Tuesday, October 27th, 2020
9:00 am – 9:30 am		Pandora's Box with Correlations: Learning and Approximation Shuchi Chawla (University of Wisconsin, Madison)
9:30 am – 10:00 am		Regret Minimization for Stochastic Shortest Paths Yishay Mansour (Tel Aviv University)
10:00 am – 10:30 am		Robust Algorithms for Secretaries and Bandits Anupam Gupta
10:30 am – 11:00 am		Discussion
11:00 am – 11:30 am		Break
11:30 am – 12:00 pm		The Non-Stochastic Control Framework Naman Agarwal (Google)
12:00 pm – 12:30 pm		Competitive Algorithms for Online Control Yisong Yue (Caltech)
12:30 pm – 1:00 pm		Discussion

Wednesday, October 28th, 2020
9:00 am – 9:30 am		A Unifying View of Optimism in Episodic Reinforcement Learning Ciara Pike-Burke (Imperial College London)
9:30 am – 10:00 am		On the Complexity of Learning Good Policies With and Without Rewards Emilie Kaufmann (CNRS & University of Lille)
10:00 am – 10:30 am		Model-Based Reinforcement Learning with Value-Targeted Regression Mengdi Wang (Princeton University)
10:30 am – 11:00 am		Discussion
11:00 am – 12:00 pm		Gather.town

Thursday, October 29th, 2020
9:00 am – 9:30 am		A Generalization Bound for Online Variational Inference Pierre Alquier (Riken AIP)
9:30 am – 10:00 am		Beating the Curse of Dimensionality in High-Dimensional Optimal Stopping David Goldberg (Cornell ORIE)
10:00 am – 10:30 am		Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization Negin Golrezaei (MIT)
10:30 am – 11:00 am		Discussion
11:00 am – 11:30 am		Break
11:30 am – 12:00 pm		Country-Scale Bandit Implementation for Targeted COVID-19 Testing Hamsa Bastani (Wharton School of the University of Pennsylvania)
12:00 pm – 12:30 pm		Multi-Player Multi-Armed Bandit: Can We Still Collaborate at Homes Without "Zoom"? Yuanzhi Li (Carnegie Mellon University)
12:30 pm – 1:00 pm		Multiplayer Bandit Learning - From Competition to Cooperation Simina Branzei (Purdue University)
1:00 pm – 1:30 pm		Discussion

Friday, October 30th, 2020
9:00 am – 9:30 am		Representation Learning and Exploration in Reinforcement Learning Akshay Krishnamurthy (Microsoft Research)
9:30 am – 10:00 am		Corruption Robust Exploration in Episodic Reinforcement Learning Aleksandrs Slivkins (Microsoft Research NYC)
10:00 am – 10:30 am		On the Global Convergence and Approximation Benefits of Policy Gradient Methods Daniel Russo (Columbia University)
10:30 am – 11:00 am		Discussion
11:00 am – 11:30 am		Break
11:30 am – 12:00 pm		An Alternative Softmax Operator for Reinforcement Learning Michael Littman (Brown University)
12:00 pm – 12:30 pm		What Are the Statistical Limits of Offline Reinforcement Learning With Function Approximation? Sham Kakade (University of Washington & Microsoft Research)
12:30 pm – 1:00 pm		Discussion