Schedule | Quantifying Uncertainty: Stochastic, Adversarial, and Beyond

8:45 – 9:10 a.m.

Coffee and Check-In

9:10 – 9:15 a.m.

Opening Remarks

9:15 – 10 a.m.

Dynamically Aggregating Diverse Information

Annie Liang (Northwestern University)

Video

10 – 10:45 a.m.

Retrospective Search: Exploration and Ambition on Uncharted Terrain

Can Urgun (Princeton University)

Video

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12 p.m.

Expert Advice in Complex Environments

Steve Callander (Stanford University)

Video

12 – 2 p.m.

Lunch

2 – 2:45 p.m.

Greedy Approximation Algorithms for Active Sequential Hypothesis Testing

Kyra Gan (Harvard University)

Video

2:45 – 3:30 p.m.

Causal Matrix Completion: Applications to Offline Causal Reinforcement Learning

Anish Agarwal (MIT)

Video

3:30 – 4 p.m.

Break

4 – 4:45 p.m.

Inference and Interference in Marketplace Experimentation

Hannah Li (Stanford)

Video

4:45 – 5:45 p.m.

Reception

8:45 – 9:15 a.m.

Coffee and Check-In

9:15 – 10 a.m.

Markovian Interference and the Differences in Q’s Estimator

Vivek Farias (Massachusetts Institute of Technology)

Video

10 – 10:45 a.m.

Causal Inference in Complex Systems: Network Interference, Strategic Agents, and Beyond

Panos Toulis (University of Chicago)

Video

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12 p.m.

Contextual Inverse Optimization: Offline and Online Learning

Ilan Lobel (NYU Stern)

Video

12 – 2 p.m.

Lunch

2 – 2:45 p.m.

Corruption-Robust Contextual Search

Chara Podimata (UC Berkeley)

Video

2:45 – 3:30 p.m.

Best of Both World Algorithms from I.I.D. to Adversarial Data

Julian Zimmert (Google Research)

Video

3:30 – 4 p.m.

Break

4 – 4:45 p.m.

Best Of Both Worlds: Stochastic & Adversarial Best-Arm Identification

Victor Gabillon (Queensland University of Technology)

Video

8:45 – 9:15 a.m.

Coffee and Check-In

9:15 a.m. – 10 p.m.

Flow Time Scheduling with Uncertain Processing Time

Yossi Azar (Tel-Aviv University)

Video

10 – 10:45 a.m.

Machine Learning for Faster Optimization

Ben Moseley (Carnegie Mellon University)

Video

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12 p.m.

Parsimonious Learning-Augmented Algorithms

Ravi Kumar (Google)

Video

12 – 12:10 p.m.

Poster Session 1 Preview (In Person Only)

12:10 – 1:40 p.m.

Lunch

1:40 – 2:40 p.m.

Poster Session 1 (In Person Only)

2:40 – 2:50 p.m.

Break

2:50 – 3:50 p.m.

Panel (In Person Only)

3:50 – 4 p.m.

Poster Session 2 Preview (In Person Only)

4 – 4:10 p.m.

Break

4:10 – 5:10 p.m.

Poster Session 2 (In Person Only)

8:45 – 9:15 a.m.

Coffee and Check-In

9:15 – 10 a.m.

Markov Persuasion Process and its Reinforcement Learning

Haifeng Xu (University of Chicago)

Video

10 – 10:45 a.m.

Attributes: Selective Learning and Influence

Arjada Bardhi (Duke University)

Video

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12 p.m.

Incentivized Exploration

Alex Slivkins (Microsoft Research)

Video

12 – 2 p.m.

Lunch

2 – 2:45 p.m.

Information Collection Through Strategic Agents

Marco Ottaviani (Bocconi University)

Video

2:45 – 3:30 p.m.

Adaptive Monopoly Regulation

Modibo Camara (Northwestern University)

Video

3:30 – 4 p.m.

Break

4 – 4:45 p.m.

Oracle-Efficient Online Learning or: How to Use Non-Robust Optimization for Robust Learning

Nika Haghtalab (UC Berkeley)

Video

8:45 – 9:15 a.m.

Coffee and Check-In

9:15 – 10 a.m.

Dynamic Regret Minimization for Bandits without Prior Knowledge

Chen-Yu Wei (University of Southern California)

Video

10 – 10:45 a.m.

When Can We Use Weak Function Approximation to Solve Large Scale Planning Problems in MDPs?

Csaba Szepesvári (University of Alberta, Google DeepMind)

Video

10:45 – 11:15 a.m.

Break

11:15 a.m. – 12 p.m.

Adaptivity and Confounding in Multi-armed Bandit Experiments

Daniel Russo (Columbia University)

Video

12 – 2 p.m.

Lunch

2 – 2:45 p.m.

Designing Experiments: Pure Exploration for Contextual Multi-armed Bandits

Emma Brunskill (Stanford University)

Video

2:45 – 3:30 p.m.

Generalization and Robustness in Offline Reinforcement Learning

Wen Sun (Cornell University)

Video