中文
相关论文

相关论文: Fast Rates for Nonparametric Online Learning: From…

200 篇论文

We show for the first time, to our knowledge, that it is possible to reconcile in online learning in zero-sum games two seemingly contradictory objectives: vanishing time-average regret and non-vanishing step sizes. This phenomenon, that we…

计算机科学与博弈论 · 计算机科学 2019-05-14 James P. Bailey , Georgios Piliouras

We study algorithms for online linear optimization in Hilbert spaces, focusing on the case where the player is unconstrained. We develop a novel characterization of a large class of minimax algorithms, recovering, and even improving,…

机器学习 · 计算机科学 2014-05-22 H. Brendan McMahan , Francesco Orabona

In the convex optimization approach to online regret minimization, many methods have been developed to guarantee a $O(\sqrt{T})$ bound on regret for subdifferentiable convex loss functions with bounded subgradients, by using a reduction to…

机器学习 · 计算机科学 2016-09-20 Arthur Flajolet , Patrick Jaillet

Universal online learning aims to achieve optimal regret guarantees without requiring prior knowledge of the curvature of online functions. Existing methods have established minimax-optimal regret bounds for universal online learning, where…

机器学习 · 计算机科学 2025-11-26 Peng Zhao , Yu-Hu Yan , Hang Yu , Zhi-Hua Zhou

In online inverse linear optimization, a learner observes time-varying sets of feasible actions and an agent's optimal actions, selected by solving linear optimization over the feasible actions. The learner sequentially makes predictions of…

机器学习 · 计算机科学 2025-05-23 Shinsaku Sakaue , Taira Tsuchiya , Han Bao , Taihei Oki

We consider online no-regret learning in unknown games with bandit feedback, where each player can only observe its reward at each time -- determined by all players' current joint action -- rather than its gradient. We focus on the class of…

机器学习 · 计算机科学 2024-04-01 Wenjia Ba , Tianyi Lin , Jiawei Zhang , Zhengyuan Zhou

We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosing a particular action. A no-regret algorithm uses these…

人工智能 · 计算机科学 2015-01-05 Kevin Waugh , Dustin Morrill , J. Andrew Bagnell , Michael Bowling

We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible…

机器学习 · 计算机科学 2024-04-09 Peng Zhao , Yu-Jie Zhang , Lijun Zhang , Zhi-Hua Zhou

We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinite-horizon discounted Markov decision process (MDP). While existing analyses of common approaches, such as fitted $Q$-iteration…

机器学习 · 计算机科学 2023-07-13 Yichun Hu , Nathan Kallus , Masatoshi Uehara

We show that natural classes of regularized learning algorithms with a form of recency bias achieve faster convergence rates to approximate efficiency and to coarse correlated equilibria in multiplayer normal form games. When each player in…

计算机科学与博弈论 · 计算机科学 2015-12-14 Vasilis Syrgkanis , Alekh Agarwal , Haipeng Luo , Robert E. Schapire

We show that learning algorithms satisfying a $\textit{low approximate regret}$ property experience fast convergence to approximate optimality in a large class of repeated games. Our property, which simply requires that each learner has…

计算机科学与博弈论 · 计算机科学 2016-12-19 Dylan J. Foster , Zhiyuan Li , Thodoris Lykouris , Karthik Sridharan , Eva Tardos

Motivated by the predictable nature of real-life in data streams, we study online regression when the learner has access to predictions about future examples. In the extreme case, called transductive online learning, the sequence of…

机器学习 · 计算机科学 2025-10-07 Vinod Raman , Shenghao Xie , Samson Zhou

Learning and computation of equilibria are central problems in game theory, theory of computation, and artificial intelligence. In this work, we introduce proximal regret, a new notion of regret based on proximal operators that lies…

计算机科学与博弈论 · 计算机科学 2025-11-06 Yang Cai , Constantinos Daskalakis , Haipeng Luo , Chen-Yu Wei , Weiqiang Zheng

We establish the first uncoupled learning algorithm that attains $O(n \log^2 d \log T)$ per-player regret in multi-player general-sum games, where $n$ is the number of players, $d$ is the number of actions available to each player, and $T$…

计算机科学与博弈论 · 计算机科学 2025-04-01 Ashkan Soleymani , Georgios Piliouras , Gabriele Farina

We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible…

机器学习 · 计算机科学 2020-12-01 Peng Zhao , Yu-Jie Zhang , Lijun Zhang , Zhi-Hua Zhou

Which classes can be learned properly in the online model? -- that is, by an algorithm that at each round uses a predictor from the concept class. While there are simple and natural cases where improper learning is necessary, it is natural…

机器学习 · 计算机科学 2021-02-03 Steve Hanneke , Roi Livni , Shay Moran

We design and analyze minimax-optimal algorithms for online linear optimization games where the player's choice is unconstrained. The player strives to minimize regret, the difference between his loss and the loss of a post-hoc benchmark…

机器学习 · 计算机科学 2013-02-12 H. Brendan McMahan

In this work, we explore online convex optimization (OCO) and introduce a new condition and analysis that provides fast rates by exploiting the curvature of feasible sets. In online linear optimization, it is known that if the average…

机器学习 · 计算机科学 2025-02-18 Taira Tsuchiya , Shinji Ito

We study various discrete nonlinear combinatorial optimization problems in an online learning framework. In the first part, we address the question of whether there are negative results showing that getting a vanishing (or even vanishing…

数据结构与算法 · 计算机科学 2020-06-24 Evripidis Bampis , Dimitris Christou , Bruno Escoffier , Nguyen Kim Thang

We study the regret of optimal strategies for online convex optimization games. Using von Neumann's minimax theorem, we show that the optimal regret in this adversarial setting is closely related to the behavior of the empirical…

机器学习 · 计算机科学 2009-04-01 Jacob Abernethy , Alekh Agarwal , Peter L. Bartlett , Alexander Rakhlin
‹ 上一页 1 2 3 10 下一页 ›