中文
相关论文

相关论文: Improved Best-of-Both-Worlds Guarantees for Multi-…

200 篇论文

The linear bandit problem has been studied for many years in both stochastic and adversarial settings. Designing an algorithm that can optimize the environment without knowing the loss type attracts lots of interest. \citet{LeeLWZ021}…

机器学习 · 计算机科学 2023-07-19 Fang Kong , Canzhe Zhao , Shuai Li

Follow-The-Regularized-Leader (FTRL) algorithms often enjoy optimal regret for adversarial as well as stochastic bandit problems and allow for a streamlined analysis. Nonetheless, FTRL algorithms require the solution of an optimization…

机器学习 · 计算机科学 2025-02-14 Mengmeng Li , Daniel Kuhn , Bahar Taşkesen

Follow-the-Regularized-Leader (FTRL) policies have achieved Best-of-Both-Worlds (BOBW) results in various settings through hybrid regularizers, whereas analogous results for Follow-the-Perturbed-Leader (FTPL) remain limited due to inherent…

机器学习 · 统计学 2025-08-27 Jongyeong Lee , Junya Honda , Shinji Ito , Min-hwan Oh

This paper studies the optimality of the Follow-the-Perturbed-Leader (FTPL) policy in both adversarial and stochastic $K$-armed bandits. Despite the widespread use of the Follow-the-Regularized-Leader (FTRL) framework with various choices…

机器学习 · 统计学 2024-03-11 Jongyeong Lee , Junya Honda , Shinji Ito , Min-hwan Oh

We consider the nonstochastic multi-agent multi-armed bandit problem with agents collaborating via a communication network with delays. We show a lower bound for individual regret of all agents. We show that with suitable regularizers and…

机器学习 · 统计学 2023-10-24 Jialin Yi , Milan Vojnović

We propose a new algorithm for adversarial multi-armed bandits with unrestricted delays. The algorithm is based on a novel hybrid regularizer applied in the Follow the Regularized Leader (FTRL) framework. It achieves…

机器学习 · 计算机科学 2020-06-17 Julian Zimmert , Yevgeny Seldin

Adaptivity to the difficulties of a problem is a key property in sequential decision-making problems to broaden the applicability of algorithms. Follow-the-regularized-leader (FTRL) has recently emerged as one of the most promising…

机器学习 · 计算机科学 2024-02-14 Taira Tsuchiya , Shinji Ito , Junya Honda

Best-of-both-worlds algorithms for online learning which achieve near-optimal regret in both the adversarial and the stochastic regimes have received growing attention recently. Existing techniques often require careful adaptation to every…

机器学习 · 计算机科学 2023-02-21 Christoph Dann , Chen-Yu Wei , Julian Zimmert

We study the decoupled multi-armed bandit problem, where the learner separately selects one arm for exploration and one, possibly different, arm for exploitation at each round. In this setting, the loss of the explored arm is observed but…

机器学习 · 统计学 2026-05-29 Chaiwon Kim , Jongyeong Lee , Min-hwan Oh

We consider the adversarial linear bandits setting and present a unified algorithmic framework that bridges Follow-the-Regularized-Leader (FTRL) and Follow-the-Perturbed-Leader (FTPL) methods, extending the known connection between them…

机器学习 · 统计学 2026-02-13 Lucas Lévy , Jean-Lou Valeau , Arya Akhavan , Patrick Rebeschini

We consider a common case of the combinatorial semi-bandit problem, the $m$-set semi-bandit, where the learner exactly selects $m$ arms from the total $d$ arms. In the adversarial setting, the best regret bound, known to be…

机器学习 · 计算机科学 2025-07-08 Jingxin Zhan , Yuchen Xin , Chenjie Sun , Zhihua Zhang

Follow-The-Regularized-Leader (FTRL) is known as an effective and versatile approach in online learning, where appropriate choice of the learning rate is crucial for smaller regret. To this end, we formulate the problem of adjusting FTRL's…

机器学习 · 计算机科学 2024-03-12 Shinji Ito , Taira Tsuchiya , Junya Honda

Heavy-tailed bandits have been extensively studied since the seminal work of \citet{Bubeck2012BanditsWH}. In particular, heavy-tailed linear bandits, enabling efficient learning with both a large number of arms and heavy-tailed noises, have…

机器学习 · 计算机科学 2025-08-20 Canzhe Zhao , Shinji Ito , Shuai Li

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…

机器学习 · 计算机科学 2024-10-24 Khashayar Gatmiry , Jon Schneider , Stefanie Jegelka

We study online convex optimization on $\ell_p$-balls in $\mathbb{R}^d$ for $p > 2$. While always sub-linear, the optimal regret exhibits a shift between the high-dimensional setting ($d > T$), when the dimension $d$ is greater than the…

机器学习 · 计算机科学 2025-12-01 Emmeran Johnson , David Martínez-Rubio , Ciara Pike-Burke , Patrick Rebeschini

The convergence analysis of online learning algorithms is central to machine learning theory, where the last-iterate convergence is particularly important, as it captures the learner's actual decisions and describes the evolution of the…

机器学习 · 计算机科学 2026-05-04 Jingxin Zhan , Yuze Han , Zhihua Zhang

We introduce the first best-of-both-worlds algorithm for contextual combinatorial semi-bandits that simultaneously guarantees $\widetilde{\mathcal{O}}(\sqrt{T})$ regret in the adversarial regime and $\widetilde{\mathcal{O}}(\ln T)$ regret…

机器学习 · 统计学 2026-03-27 Mengmeng Li , Philipp J. Schneider , Jelisaveta Aleksić , Daniel Kuhn

This paper studies the optimality and complexity of Follow-the-Perturbed-Leader (FTPL) policy in $m$-set semi-bandit problems. FTPL has been studied extensively as a promising candidate of an efficient algorithm with favorable regret for…

机器学习 · 计算机科学 2026-03-13 Botao Chen , Jongyeong Lee , Chansoo Kim , Junya Honda

Existing data-dependent and best-of-both-worlds regret bounds for multi-armed bandits problems have limited adaptivity as they are either data-dependent but not best-of-both-worlds (BOBW), BOBW but not data-dependent or have sub-optimal…

机器学习 · 计算机科学 2025-02-13 Quan Nguyen , Shinji Ito , Junpei Komiyama , Nishant A. Mehta

The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing research effort into new technologies, performing clinical trials, and hyperparameter selection…

机器学习 · 计算机科学 2026-05-22 Avrim Blum , Marten Garicano , Kavya Ravichandran , Dravyansh Sharma
‹ 上一页 1 2 3 10 下一页 ›