中文
相关论文

相关论文: Relaxing the I.I.D. Assumption: Adaptively Minimax…

200 篇论文

Quantile (and, more generally, KL) regret bounds, such as those achieved by NormalHedge (Chaudhuri, Freund, and Hsu 2009) and its variants, relax the goal of competing against the best individual expert to only competing against a majority…

机器学习 · 统计学 2021-11-09 Jeffrey Negrea , Blair Bilodeau , Nicolò Campolongo , Francesco Orabona , Daniel M. Roy

Follow-the-Regularized-Leader (FTRL) is a powerful framework for various online learning problems. By designing its regularizer and learning rate to be adaptive to past observations, FTRL is known to work adaptively to various properties of…

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

In this paper, we study the behavior of the Hedge algorithm in the online stochastic setting. We prove that anytime Hedge with decreasing learning rate, which is one of the simplest algorithm for the problem of prediction with expert…

机器学习 · 统计学 2019-07-10 Jaouad Mourtada , Stéphane Gaïffas

Regret minimization is a powerful method for finding Nash equilibria in Normal-Form Games (NFGs) and Extensive-Form Games (EFGs), but it typically guarantees convergence only for the average strategy. However, computing the average strategy…

计算机科学与博弈论 · 计算机科学 2025-09-18 Hang Ren , Yulin Wu , Shuhan Qi , Jiajia Zhang , Xiaozhen Sun , Tianzi Ma , Xuan Wang

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 2022-06-09 Sarah Sachs , Hédi Hadiji , Tim van Erven , Cristóbal Guzmán

We study online learning in adversarial nonstationary environments. Since the future can be very different from the past, a critical challenge is to gracefully forget the history while new data comes in. To formalize this intuition, we…

机器学习 · 计算机科学 2024-06-21 Zhiyu Zhang , David Bombara , Heng Yang

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

We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic…

机器学习 · 计算机科学 2024-01-26 Hao Liang , Zhi-Quan Luo

Most methods for decision-theoretic online learning are based on the Hedge algorithm, which takes a parameter called the learning rate. In most previous analyses the learning rate was carefully tuned to obtain optimal worst-case…

机器学习 · 统计学 2015-03-04 Tim van Erven , Peter Grünwald , Wouter M. Koolen , Steven de Rooij

We revisit the classic regret-minimization problem in the stochastic multi-armed bandit setting when the arm-distributions are allowed to be heavy-tailed. Regret minimization has been well studied in simpler settings of either bounded…

机器学习 · 计算机科学 2021-02-09 Shubhada Agrawal , Sandeep Juneja , Wouter M. Koolen

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

We consider learning in an adversarial Markov Decision Process (MDP) where the loss functions can change arbitrarily over $K$ episodes and the state space can be arbitrarily large. We assume that the Q-function of any policy is linear in…

机器学习 · 计算机科学 2023-06-05 Yan Dai , Haipeng Luo , Chen-Yu Wei , Julian Zimmert

In this work, we consider the problem of regret minimization in adaptive minimum variance and linear quadratic control problems. Regret minimization has been extensively studied in the literature for both types of adaptive control problems.…

最优化与控制 · 数学 2022-11-16 Kévin Colin , Håkan Hjalmarsson , Xavier Bombois

We study a regret minimization problem with the existence of multiple best/near-optimal arms in the multi-armed bandit setting. We consider the case when the number of arms/actions is comparable or much larger than the time horizon, and…

机器学习 · 统计学 2020-10-23 Yinglun Zhu , Robert Nowak

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

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

Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a…

机器学习 · 计算机科学 2017-09-12 Pooria Joulani , András György , Csaba Szepesvári

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

We study the problem of designing adaptive multi-armed bandit algorithms that perform optimally in both the stochastic setting and the adversarial setting simultaneously (often known as a best-of-both-world guarantee). A line of recent…

机器学习 · 计算机科学 2023-10-27 Tiancheng Jin , Junyan Liu , Haipeng Luo

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
‹ 上一页 1 2 3 10 下一页 ›