中文
相关论文

相关论文: Optimal Non-Asymptotic Lower Bound on the Minimax …

200 篇论文

We revisit the problem of stochastic online learning with feedback graphs, with the goal of devising algorithms that are optimal, up to constants, both asymptotically and in finite time. We show that, surprisingly, the notion of optimal…

机器学习 · 计算机科学 2022-06-22 Teodor V. Marinov , Mehryar Mohri , 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 discuss a general approach to building non-asymptotic confidence bounds for stochastic optimization problems. Our principal contribution is the observation that a Sample Average Approximation of a problem supplies upper and lower bounds…

最优化与控制 · 数学 2016-12-13 Vincent Guigues , Anatoli Juditsky , Arkadi Nemirovski

This paper establishes that optimistic algorithms attain gap-dependent and non-asymptotic logarithmic regret for episodic MDPs. In contrast to prior work, our bounds do not suffer a dependence on diameter-like quantities or ergodicity, and…

机器学习 · 计算机科学 2019-10-30 Max Simchowitz , Kevin Jamieson

We propose information-directed sampling -- a new approach to online optimization problems in which a decision-maker must balance between exploration and exploitation while learning from partial feedback. Each action is sampled in a manner…

机器学习 · 计算机科学 2017-07-10 Daniel Russo , Benjamin Van Roy

We introduce a novel extension of the canonical multi-armed bandit problem that incorporates an additional strategic innovation: abstention. In this enhanced framework, the agent is not only tasked with selecting an arm at each time step,…

机器学习 · 计算机科学 2026-03-24 Junwen Yang , Tianyuan Jin , Vincent Y. F. Tan

The regret bound of dynamic online learning algorithms is often expressed in terms of the variation in the function sequence ($V_T$) and/or the path-length of the minimizer sequence after $T$ rounds. For strongly convex and smooth…

机器学习 · 计算机科学 2020-08-17 Ting-Jui Chang , Shahin Shahrampour

This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in advance and hence selects the minimizer of the loss function at…

机器学习 · 计算机科学 2016-05-17 Tianbao Yang , Lijun Zhang , Rong Jin , Jinfeng Yi

We determine the minimax optimal expected regret in the classic non-stochastic multi-armed bandit with expert advice problem, by proving a lower bound that matches the upper bound of Kale (2014). The two bounds determine the minimax optimal…

机器学习 · 计算机科学 2025-11-04 Zachary Chase , Shinji Ito , Idan Mehalel

We study online inverse linear optimization, also known as contextual recommendation, where a learner sequentially infers an agent's hidden objective vector from observed optimal actions over feasible sets that change over time. The learner…

机器学习 · 计算机科学 2026-05-13 Taihei Oki , Shinsaku Sakaue

The standard theory of optimal stopping is based on the idealised assumption that the underlying process is essentially known. In this paper, we drop this restriction and study data-driven optimal stopping for a general diffusion process,…

统计理论 · 数学 2023-12-12 Sören Christensen , Niklas Dexheimer , Claudia Strauch

We demonstrate that, in the classical non-stochastic regret minimization problem with $d$ decisions, gains and losses to be respectively maximized or minimized are fundamentally different. Indeed, by considering the additional sparsity…

机器学习 · 计算机科学 2015-11-30 Joon Kwon , Vianney Perchet

Some of the most compelling applications of online convex optimization, including online prediction and classification, are unconstrained: the natural feasible set is R^n. Existing algorithms fail to achieve sub-linear regret in this…

机器学习 · 计算机科学 2012-11-13 Matthew Streeter , H. Brendan McMahan

In this work, we improve on the upper and lower bounds for the regret of online learning with strongly observable undirected feedback graphs. The best known upper bound for this problem is $\mathcal{O}\bigl(\sqrt{\alpha T\ln K}\bigr)$,…

机器学习 · 计算机科学 2023-10-31 Khaled Eldowa , Emmanuel Esposito , Tommaso Cesari , Nicolò Cesa-Bianchi

We study online prediction of bounded stationary ergodic processes. To do so, we consider the setting of prediction of individual sequences and build a deterministic regression tree that performs asymptotically as well as the best…

统计理论 · 数学 2014-05-12 Pierre Gaillard , Paul Baudin

In this paper, we study gap-dependent regret guarantees for risk-sensitive reinforcement learning based on the entropic risk measure. We propose a novel definition of sub-optimality gaps, which we call cascaded gaps, and we discuss their…

机器学习 · 计算机科学 2022-03-08 Yingjie Fei , Ruitu Xu

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

We derive sublinear regret bounds for undiscounted reinforcement learning in continuous state space. The proposed algorithm combines state aggregation with the use of upper confidence bounds for implementing optimism in the face of…

机器学习 · 计算机科学 2013-02-12 Ronald Ortner , Daniil Ryabko

We address the online linear optimization problem with bandit feedback. Our contribution is twofold. First, we provide an algorithm (based on exponential weights) with a regret of order $\sqrt{d n \log N}$ for any finite action set with $N$…

机器学习 · 计算机科学 2012-02-15 Sébastien Bubeck , Nicolò Cesa-Bianchi , Sham M. Kakade

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
‹ 上一页 1 2 3 10 下一页 ›