Search Results for author:
Found 36 papers, 3 papers with code
Do LLM Agents Have Regret? A Case Study in Online Learning and Games
To better understand the limits of LLM agents in these interactive environments, we propose to study their interactions in benchmark decision-making settings in online learning and game theory, through the performance metric of \emph{regret}.
Matching of Users and Creators in Two-Sided Markets with Departures
Most of the existing literature on platform recommendation algorithms largely focuses on user preferences and decisions, and does not simultaneously address creator incentives.
Two-Timescale Q-Learning with Function Approximation in Zero-Sum Stochastic Games
Specifically, through a change of variable, we show that the update equation of the slow-timescale iterates resembles the classical smoothed best-response dynamics, where the regularized Nash gap serves as a valid Lyapunov function.
EM for Mixture of Linear Regression with Clustered Data
In many settings however, heterogeneous data may be generated in clusters with shared structures, as is the case in several applications such as federated learning where a common latent variable governs the distribution of all the samples generated by a client.
Multi-Player Zero-Sum Markov Games with Networked Separable Interactions
We study a new class of Markov games, \emph(multi-player) zero-sum Markov Games} with \emph{Networked separable interactions} (zero-sum NMGs), to model the local interaction structure in non-cooperative multi-agent sequential decision-making.
Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation
Offline reinforcement learning (RL) aims to find an optimal policy for sequential decision-making using a pre-collected dataset, without further interaction with the environment.
Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence
We also generalize the results to certain function approximation settings.
The Power of Regularization in Solving Extensive-Form Games
Second, we show that regularized counterfactual regret minimization (\texttt{Reg-CFR}), with a variant of optimistic mirror descent algorithm as regret-minimizer, can achieve $O(1/T^{1/4})$ best-iterate, and $O(1/T^{3/4})$ average-iterate convergence rate for finding NE in EFGs.
What is a Good Metric to Study Generalization of Minimax Learners?
Minimax optimization has served as the backbone of many machine learning (ML) problems.
Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms
We consider a platform's problem of collecting data from privacy sensitive users to estimate an underlying parameter of interest.
Independent Learning in Stochastic Games
We focus on the development of simple and independent learning dynamics for stochastic games: each agent is myopic and chooses best-response type actions to other agents' strategy without any coordination with her opponent.
A Wasserstein Minimax Framework for Mixed Linear Regression
We propose an optimal transport-based framework for MLR problems, Wasserstein Mixed Linear Regression (WMLR), which minimizes the Wasserstein distance between the learned and target mixture regression models.
Decentralized Q-Learning in Zero-sum Markov Games
The key challenge in this decentralized setting is the non-stationarity of the environment from an agent's perspective, since both her own payoffs and the system evolution depend on the actions of other agents, and each agent adapts her policies simultaneously and independently.
Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks
In this paper, we study the generalization properties of Model-Agnostic Meta-Learning (MAML) algorithms for supervised learning problems.
Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach
In this paper, we study a personalized variant of the federated learning in which our goal is to find an initial shared model that current or new users can easily adapt to their local dataset by performing one or a few steps of gradient descent with respect to their own data.
Train simultaneously, generalize better: Stability of gradient-based minimax learners
In this paper, we show that the optimization algorithm also plays a key role in the generalization performance of the trained minimax model.
Multi-agent Bayesian Learning with Adaptive Strategies: Convergence and Stability
Any fixed point belief consistently estimates the payoff distribution given the fixed point strategy profile.
Fictitious play in zero-sum stochastic games
We present a novel variant of fictitious play dynamics combining classical fictitious play with Q-learning for stochastic games and analyze its convergence properties in two-player zero-sum stochastic games.
Bayesian Learning with Adaptive Load Allocation Strategies
We study a Bayesian learning dynamics induced by agents who repeatedly allocate loads on a set of resources based on their belief of an unknown parameter that affects the cost distributions of resources.
GANs May Have No Nash Equilibria
We discuss several numerical experiments demonstrating the existence of proximal equilibrium solutions in GAN minimax problems.
Personalized Federated Learning: A Meta-Learning Approach
In this paper, we study a personalized variant of the federated learning in which our goal is to find an initial shared model that current or new users can easily adapt to their local dataset by performing one or a few steps of gradient descent with respect to their own data.
An Optimal Multistage Stochastic Gradient Method for Minimax Problems
Next, we propose a multistage variant of stochastic GDA (M-GDA) that runs in multiple stages with a particular learning rate decay schedule and converges to the exact solution of the minimax problem.
On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning
We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcement Learning (RL) problems, where the goal is to find a policy using data from several tasks represented by Markov Decision Processes (MDPs) that can be updated by one step of stochastic policy gradient for the realized MDP.
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.
A Decentralized Proximal Point-type Method for Saddle Point Problems
In this paper, we focus on solving a class of constrained non-convex non-concave saddle point problems in a decentralized manner by a group of nodes in a network.
Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks
When gradients do not contain noise, we also prove that distributed accelerated methods can \emph{achieve acceleration}, requiring $\mathcal{O}(\kappa \log(1/\varepsilon))$ gradient evaluations and $\mathcal{O}(\kappa \log(1/\varepsilon))$ communications to converge to the same fixed point with the non-accelerated variant where $\kappa$ is the condition number and $\varepsilon$ is the target accuracy.
On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms
We study the convergence of a class of gradient-based Model-Agnostic Meta-Learning (MAML) methods and characterize their overall complexity as well as their best achievable accuracy in terms of gradient norm for nonconvex loss functions.
Convergence Rate of $\mathcal{O}(1/k)$ for Optimistic Gradient and Extra-gradient Methods in Smooth Convex-Concave Saddle Point Problems
To do so, we first show that both OGDA and EG can be interpreted as approximate variants of the proximal point method.
A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
In this paper we consider solving saddle point problems using two variants of Gradient Descent-Ascent algorithms, Extra-gradient (EG) and Optimistic Gradient Descent Ascent (OGDA) methods.
A Universally Optimal Multistage Accelerated Stochastic Gradient Method
We study the problem of minimizing a strongly convex, smooth function when we have noisy estimates of its gradient.
Escaping Saddle Points in Constrained Optimization
We propose a generic framework that yields convergence to a second-order stationary point of the problem, if the convex set $\mathcal{C}$ is simple for a quadratic objective function.
Convergence Rate of Block-Coordinate Maximization Burer-Monteiro Method for Solving Large SDPs
Furthermore, incorporating Lanczos method to the block-coordinate maximization, we propose an algorithm that is guaranteed to return a solution that provides $1-O(1/r)$ approximation to the original SDP without any assumptions, where $r$ is the rank of the factorization.
Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions
We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm.
When Cyclic Coordinate Descent Outperforms Randomized Coordinate Descent
The coordinate descent (CD) method is a classical optimization algorithm that has seen a revival of interest because of its competitive performance in machine learning applications.
Computing the Stationary Distribution Locally
In this paper, we provide a novel algorithm that answers whether a chosen state in a MC has stationary probability larger than some $\Delta \in (0, 1)$.
Distributed Subgradient Methods and Quantization Effects
We consider a convex unconstrained optimization problem that arises in a network of agents whose goal is to cooperatively optimize the sum of the individual agent objective functions through local computations and communications.
Optimization and Control
