中文
相关论文

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

200 篇论文

We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of…

机器学习 · 计算机科学 2019-09-24 Arun Sai Suggala , Praneeth Netrapalli

We consider online learning problems in the realizable setting, where there is a zero-loss solution, and propose new Differentially Private (DP) algorithms that obtain near-optimal regret bounds. For the problem of online prediction from…

机器学习 · 计算机科学 2023-03-01 Hilal Asi , Vitaly Feldman , Tomer Koren , Kunal Talwar

We study the framework of universal dynamic regret minimization with strongly convex losses. We answer an open problem in Baby and Wang 2021 by showing that in a proper learning setup, Strongly Adaptive algorithms can achieve the near…

机器学习 · 计算机科学 2022-01-25 Dheeraj Baby , Yu-Xiang Wang

Sequential learning with feedback graphs is a natural extension of the multi-armed bandit problem where the problem is equipped with an underlying graph structure that provides additional information - playing an action reveals the losses…

机器学习 · 计算机科学 2023-06-06 Tomáš Kocák , Alexandra Carpentier

Regret minimization is a general approach to online optimization which plays a crucial role in many algorithms for approximating Nash equilibria in two-player zero-sum games. The literature mainly focuses on solving individual games in…

计算机科学与博弈论 · 计算机科学 2025-04-29 David Sychrovský , Martin Schmid , Michal Šustr , Michael Bowling

This study considers online learning with general directed feedback graphs. For this problem, we present best-of-both-worlds algorithms that achieve nearly tight regret bounds for adversarial environments as well as poly-logarithmic regret…

机器学习 · 计算机科学 2022-12-29 Shinji Ito , Taira Tsuchiya , Junya Honda

We consider the fundamental problem of prediction with expert advice where the experts are "optimizable": there is a black-box optimization oracle that can be used to compute, in constant time, the leading expert in retrospect at any point…

机器学习 · 计算机科学 2016-01-28 Elad Hazan , Tomer Koren

We examine the problem of regret minimization when the learner is involved in a continuous game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is possible to achieve significantly lower regret…

计算机科学与博弈论 · 计算机科学 2023-03-20 Yu-Guan Hsieh , Kimon Antonakopoulos , Volkan Cevher , Panayotis Mertikopoulos

The goal of a learner in standard online learning is to maintain an average loss close to the loss of the best-performing single function in some class. In many real-world problems, such as rating or ranking items, there is no single best…

机器学习 · 计算机科学 2013-03-18 Edward Moroshko , Koby Crammer

We consider the problem of online classification under a privacy constraint. In this setting a learner observes sequentially a stream of labelled examples $(x_t, y_t)$, for $1 \leq t \leq T$, and returns at each iteration $t$ a hypothesis…

机器学习 · 计算机科学 2021-06-28 Noah Golowich , Roi Livni

Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop…

机器学习 · 计算机科学 2015-01-27 Ali Jadbabaie , Alexander Rakhlin , Shahin Shahrampour , Karthik Sridharan

Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions. For example, given a classifier that determines loan approval based on credit scores, applicants may open…

机器学习 · 计算机科学 2026-02-09 Chase Hutton , Adam Melrod , Han Shao

Regret minimization has proved to be a versatile tool for tree-form sequential decision making and extensive-form games. In large two-player zero-sum imperfect-information games, modern extensions of counterfactual regret minimization (CFR)…

计算机科学与博弈论 · 计算机科学 2021-03-09 Gabriele Farina , Tuomas Sandholm

Regret matching (RM) -- and its modern variants -- is a foundational online algorithm that has been at the heart of many AI breakthrough results in solving benchmark zero-sum games, such as poker. Yet, surprisingly little is known so far in…

计算机科学与博弈论 · 计算机科学 2025-11-18 Ioannis Anagnostides , Emanuel Tewolde , Brian Hu Zhang , Ioannis Panageas , Vincent Conitzer , Tuomas Sandholm

We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and…

机器学习 · 计算机科学 2017-11-06 Elad Hazan , Karan Singh , Cyril Zhang

We consider the problem of minimizing different notions of swap regret in online optimization. These forms of regret are tightly connected to correlated equilibrium concepts in games, and have been more recently shown to guarantee…

机器学习 · 计算机科学 2026-05-22 Ioannis Anagnostides , Gabriele Farina , Maxwell Fishelson , Haipeng Luo , Jon Schneider

We study adversarial online nonparametric regression with general convex losses and propose a parameter-free learning algorithm that achieves minimax optimal rates. Our approach leverages chaining trees to compete against H{\"o}lder…

统计理论 · 数学 2025-04-14 Paul Liautaud , Pierre Gaillard , Olivier Wintenberger

In this paper, we investigate the existence of online learning algorithms with bandit feedback that simultaneously guarantee $O(1)$ regret compared to a given comparator strategy, and $\tilde{O}(\sqrt{T})$ regret compared to any fixed…

机器学习 · 计算机科学 2025-06-05 Adrian Müller , Jon Schneider , Stratis Skoulakis , Luca Viano , Volkan Cevher

Stochastic and adversarial data are two widely studied settings in online learning. But many optimization tasks are neither i.i.d. nor fully adversarial, which makes it of fundamental interest to get a better theoretical understanding of…

机器学习 · 计算机科学 2025-11-03 Sarah Sachs , Hedi Hadiji , Tim van Erven , Cristobal Guzman

We study Online Convex Optimization (OCO) with adversarial constraints, where an online algorithm must make sequential decisions to minimize both convex loss functions and cumulative constraint violations. We focus on a setting where the…

机器学习 · 统计学 2025-03-14 Jordan Lekeufack , Michael I. Jordan