Prof. Zico Kolter
Deep Equilibrium Models: One (Implicit) Layer is All You Need

Behrooz Tahmasebi
Recursive Neighborhood Pooling for Graph Representation Learning

Lei Xu
Attacking Text Classifiers via Sentence Rewriting Sampler

Sitan Chen
Learning Deep ReLU Networks Is Fixed-Parameter Tractable

Josh Gruenstein
Residual Model Learning for Micro-Robot Control

Yi Tian
Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes

Parker Lusk
CLIPPER: A Graph-Theoretic Framework for Robust Data Association

Anubhav Guha
MRAC-RL: A Framework for On-Line Policy Adaptation Under Parametric Model Uncertainty

Juncal Arbelaiz
Can Noise Induce Sparsity?

Yingnan Cui
Fast Convergence of Performance Error and Parameter Error with Excitation

Anurag Ajay
Offline Primitive Discovery for Accelerating Offline Reinforcement Learning

Hanzhang Qin
Provably Sample-Efficient Inventory Control

Bharadwaj Satchidanandan
An Efficient and Incentive-Compatible Mechanism for Energy Storage Markets

Prof. Kimon Drakopoulos
Deploying a Data-Driven COVID-19 Screening Policy at the Greek Border

Max Li
Top-Down Control of Airport Network Delays

Micah Smith
A New Approach to Collaborative Data Science with the Ballet Framework

Muhammed Sayin
Fictitious Play in Zero-sum Stochastic Games

Anish Agarwal
Synthetic Interventions

Chin-Chia Hsu
Verification, Disclosure and Network Formation in News Subscription Services

Chandler Squires
Causal Imputation via Synthetic Interventions

Chenyang Yuan
Semidefinite Relaxations of Product of PSD Forms

Tobia Marcucci
Shortest Paths in Graphs of Convex Sets

Shuvomoy Das Gupta
Exterior-point Operator Splitting for Nonconvex Learning

Yunzong Xu
On Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning

Eren C. Kizildag
The Landscape of the Number Partitioning Problem and the Overlap Gap Property

Jason Altschuler
Settling the Computational Complexity of Wasserstein Barycenters