English
Related papers

Related papers: The Power of Regularization in Solving Extensive-F…

200 papers

Online mirror descent (OMD) and dual averaging (DA) -- two fundamental algorithms for online convex optimization -- are known to have very similar (and sometimes identical) performance guarantees when used with a fixed learning rate. Under…

Machine Learning · Computer Science 2021-09-07 Huang Fang , Nicholas J. A. Harvey , Victor S. Portella , Michael P. Friedlander

Counterfactual Regret Minimization (CFR) is the leading framework for solving large imperfect-information games. It converges to an equilibrium by iteratively traversing the game tree. In order to deal with extremely large games,…

Artificial Intelligence · Computer Science 2019-05-23 Noam Brown , Adam Lerer , Sam Gross , Tuomas Sandholm

Different types of dynamics have been studied in repeated game play, and one of them which has received much attention recently consists of those based on "no-regret" algorithms from the area of machine learning. It is known that dynamics…

Computer Science and Game Theory · Computer Science 2016-10-14 Po-An Chen , Chi-Jen Lu

Neural Networks (NNs) for causal effect estimation have shown strong empirical performance, yet endowing them with desirable semiparametric properties -- doubly robustness and fast convergence rates -- remains challenging. A common approach…

Machine Learning · Computer Science 2026-05-25 Jiahong Li , Zeqin Yang , Jixing Xu , Enzheng Hua , Zhichao Zou , Peng Zhen , Jiecheng Guo

We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call "optimistic closure," which is…

Machine Learning · Statistics 2019-12-10 Yining Wang , Ruosong Wang , Simon S. Du , Akshay Krishnamurthy

The congestion game is a powerful model that encompasses a range of engineering systems such as traffic networks and resource allocation. It describes the behavior of a group of agents who share a common set of $F$ facilities and take…

Computer Science and Game Theory · Computer Science 2023-06-27 Jing Dong , Jingyu Wu , Siwei Wang , Baoxiang Wang , Wei Chen

We present tools for the analysis of Follow-The-Regularized-Leader (FTRL), Dual Averaging, and Mirror Descent algorithms when the regularizer (equivalently, prox-function or learning rate schedule) is chosen adaptively based on the data.…

Machine Learning · Computer Science 2015-11-10 H. Brendan McMahan

Non-ergodic convergence of learning dynamics in games is widely studied recently because of its importance in both theory and practice. Recent work (Cai et al., 2024) showed that a broad class of learning dynamics, including Optimistic…

Machine Learning · Computer Science 2025-03-05 Yang Cai , Gabriele Farina , Julien Grand-Clément , Christian Kroer , Chung-Wei Lee , Haipeng Luo , Weiqiang Zheng

Last-iterate behaviors of learning algorithms in repeated two-player zero-sum games have been extensively studied due to their wide applications in machine learning and related tasks. Typical algorithms that exhibit the last-iterate…

Machine Learning · Computer Science 2024-06-18 Yi Feng , Ping Li , Ioannis Panageas , Xiao Wang

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

Machine Learning · Computer Science 2019-02-08 Chaobing Song , Ji Liu , Han Liu , Yong Jiang , Tong Zhang

In this paper, we investigate the impact of introducing relative entropy regularization on the Nash Equilibria (NE) of General-Sum $N$-agent games, revealing the fact that the NE of such games conform to linear Gaussian policies. Moreover,…

Computer Science and Game Theory · Computer Science 2024-09-16 Muhammad Aneeq uz Zaman , Shubham Aggarwal , Melih Bastopcu , Tamer Başar

In iterative approaches to empirical game-theoretic analysis (EGTA), the strategy space is expanded incrementally based on analysis of intermediate game models. A common approach to strategy exploration, represented by the double oracle…

Computer Science and Game Theory · Computer Science 2023-02-13 Yongzhao Wang , Michael P. Wellman

In this paper, we consider Riemannian online convex optimization with dynamic regret. First, we propose two novel algorithms, namely the Riemannian Online Optimistic Gradient Descent (R-OOGD) and the Riemannian Adaptive Online Optimistic…

Optimization and Control · Mathematics 2023-08-31 Xi Wang , Deming Yuan , Yiguang Hong , Zihao Hu , Lei Wang , Guodong Shi

Counterfactual Regret Minimization (CFR) and its variants are widely recognized as effective algorithms for solving extensive-form imperfect information games. Recently, many improvements have been focused on enhancing the convergence speed…

Artificial Intelligence · Computer Science 2024-10-29 Ju Qi , Falin Hei , Ting Feng , Dengbing Yi , Zhemei Fang , Yunfeng Luo

In two-player zero-sum games, if both players minimize their average external regret, then the average of the strategy profiles converges to a Nash equilibrium. For n-player general-sum games, however, theoretical guarantees for regret…

Computer Science and Game Theory · Computer Science 2013-05-02 Richard Gibson

Extensive-form games (EFGs) provide a powerful framework for modeling sequential decision making, capturing strategic interaction under imperfect information, chance events, and temporal structure. Most positive algorithmic and theoretical…

Computer Science and Game Theory · Computer Science 2026-05-26 Rui Zheng , Ryann Sim , Antonios Varvitsiotis

Follow-the-Regularized-Leader (FTRL) algorithms are a popular class of learning algorithms for online linear optimization (OLO) that guarantee sub-linear regret, but the choice of regularizer can significantly impact dimension-dependent…

Machine Learning · Computer Science 2024-10-24 Khashayar Gatmiry , Jon Schneider , Stefanie Jegelka

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

We study fast rates of convergence in the setting of nonparametric online regression, namely where regret is defined with respect to an arbitrary function class which has bounded complexity. Our contributions are two-fold: - In the…

Machine Learning · Computer Science 2022-04-13 Constantinos Daskalakis , Noah Golowich

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the…

Machine Learning · Computer Science 2026-03-12 Heyang Zhao , Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang