research
∙
09/21/2023
Smooth Nash Equilibria: Algorithms and Complexity
A fundamental shortcoming of the concept of Nash equilibrium is its comp...
share
research
∙
09/18/2023
Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles
The key assumption underlying linear Markov Decision Processes (MDPs) is...
research
∙
05/01/2023
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
A central problem in the theory of multi-agent reinforcement learning (M...
research
∙
03/22/2023
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games
We consider the problem of decentralized multi-agent reinforcement learn...
research
∙
01/19/2023
Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient
A foundational problem in reinforcement learning and interactive decisio...
research
∙
11/25/2022
A Note on Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
We consider the problem of interactive decision making, encompassing str...
research
∙
10/18/2022
STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games
Min-max optimization problems involving nonconvex-nonconcave objectives ...
research
∙
06/07/2022
Learning in Observable POMDPs, without Computationally Intractable Oracles
Much of reinforcement learning theory is built on top of oracles that ar...
research
∙
04/08/2022
The Complexity of Markov Equilibrium in Stochastic Games
We show that computing approximate stationary Markov coarse correlated e...
research
∙
02/09/2022
Smoothed Online Learning is as Easy as Statistical Learning
Much of modern learning theory has been split between two regimes: the c...
research
∙
01/12/2022
Planning in Observable POMDPs in Quasipolynomial Time
Partially Observable Markov Decision Processes (POMDPs) are a natural an...
research
∙
11/24/2021
Differentially Private Nonparametric Regression Under a Growth Condition
Given a real-valued hypothesis class ℋ, we investigate under what condit...
research
∙
11/17/2021
Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games
We study fast rates of convergence in the setting of nonparametric onlin...
research
∙
11/11/2021
Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games
Recently, Daskalakis, Fishelson, and Golowich (DFG) (NeurIPS`21) showed ...
research
∙
10/25/2021
Can Q-Learning be Improved with Advice?
Despite rapid progress in theoretical reinforcement learning (RL) over t...
research
∙
08/16/2021
Near-Optimal No-Regret Learning in General Games
We show that Optimistic Hedge – a common variant of multiplicative-weigh...
research
∙
06/25/2021
Littlestone Classes are Privately Online Learnable
We consider the problem of online classification under a privacy constra...
research
∙
02/11/2021
On Deep Learning with Label Differential Privacy
In many machine learning applications, the training data can contain hig...
research
∙
01/11/2021
Independent Policy Gradient Methods for Competitive Reinforcement Learning
We obtain global, non-asymptotic convergence guarantees for independent ...
research
∙
12/07/2020
Sample-efficient proper PAC learning with approximate differential privacy
In this paper we prove that the sample complexity of properly learning a...
research
∙
10/26/2020
Tight last-iterate convergence rates for no-regret learning in multi-player games
We study the question of obtaining last-iterate convergence rates for no...
research
∙
07/07/2020
Near-tight closure bounds for Littlestone and threshold dimensions
We study closure properties for the Littlestone and threshold dimensions...
research
∙
02/05/2020
Pure Differentially Private Summation from Anonymous Messages
The shuffled (aka anonymous) model has recently generated significant in...
research
∙
01/31/2020
Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems
In this paper we study the smooth convex-concave saddle point problem. S...
research
∙
09/01/2019
Round Complexity of Common Randomness Generation: The Amortized Setting
We study the effect of rounds of interaction on the common randomness ge...
research
∙
08/29/2019
Private Heavy Hitters and Range Queries in the Shuffled Model
An exciting new development in differential privacy is the shuffled mode...
research
∙
10/04/2018
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks
We analyze speed of convergence to global optimum for gradient descent t...
research
∙
08/27/2018
Communication-Rounds Tradeoffs for Common Randomness and Secret Key Generation
We study the role of interaction in the Common Randomness Generation (CR...
research
∙
01/07/2018
Theory of Deep Learning IIb: Optimization Properties of SGD
In Theory IIb we characterize with a mix of theory and experiments the o...
research
∙
12/18/2017