English
Related papers

Related papers: Eluder dimension: localise it!

200 papers

We consider the problem of learning to optimize an unknown Markov decision process (MDP). We show that, if the MDP can be parameterized within some known function class, we can obtain regret bounds that scale with the dimensionality, rather…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

We provide new insights on eluder dimension, a complexity measure that has been extensively used to bound the regret of algorithms for online bandits and reinforcement learning with function approximation. First, we study the relationship…

Machine Learning · Computer Science 2022-10-06 Gene Li , Pritish Kamath , Dylan J. Foster , Nathan Srebro

Obtaining first-order regret bounds -- regret bounds scaling not as the worst-case but with some measure of the performance of the optimal policy on a given instance -- is a core question in sequential decision-making. While such bounds…

Machine Learning · Computer Science 2022-10-24 Andrew Wagenmaker , Yifang Chen , Max Simchowitz , Simon S. Du , Kevin Jamieson

Eluder dimension and information gain are two widely used methods of complexity measures in bandit and reinforcement learning. Eluder dimension was originally proposed as a general complexity measure of function classes, but the common…

Machine Learning · Computer Science 2021-07-07 Kaixuan Huang , Sham M. Kakade , Jason D. Lee , Qi Lei

Recently, there has been remarkable progress in reinforcement learning (RL) with general function approximation. However, all these works only provide regret or sample complexity guarantees. It is still an open question if one can achieve…

Machine Learning · Computer Science 2023-05-16 Yue Wu , Jiafan He , Quanquan Gu

Regret bounds in online learning compare the player's performance to $L^*$, the optimal performance in hindsight with a fixed strategy. Typically such bounds scale with the square root of the time horizon $T$. The more refined concept of…

Machine Learning · Computer Science 2018-02-12 Zeyuan Allen-Zhu , Sébastien Bubeck , Yuanzhi Li

We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in minimax bounds, we show that the eluder dimension…

Machine Learning · Computer Science 2024-11-28 Zeyu Jia , Jian Qian , Alexander Rakhlin , Chen-Yu Wei

In this paper, we study both multi-armed and contextual bandit problems in censored environments. Our goal is to estimate the performance loss due to censorship in the context of classical algorithms designed for uncensored environments.…

Machine Learning · Computer Science 2023-02-15 Gauthier Guinet , Saurabh Amin , Patrick Jaillet

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

We revisit the sequential variants of linear regression with the squared loss, classification problems with hinge loss, and logistic regression, all characterized by unbounded losses in the setup where no assumptions are made on the…

Machine Learning · Statistics 2025-09-08 Jian Qian , Alexander Rakhlin , Nikita Zhivotovskiy

Generalized Linear Bandits (GLBs) are powerful extensions to the Linear Bandit (LB) setting, broadening the benefits of reward parametrization beyond linearity. In this paper we study GLBs in non-stationary environments, characterized by a…

Machine Learning · Computer Science 2021-03-11 Louis Faury , Yoan Russac , Marc Abeille , Clément Calauzènes

In this paper, we consider the multi-armed bandit problem with high-dimensional features. First, we prove a minimax lower bound, $\mathcal{O}\big((\log d)^{\frac{\alpha+1}{2}}T^{\frac{1-\alpha}{2}}+\log T\big)$, for the cumulative regret,…

Machine Learning · Computer Science 2021-09-27 Ke Li , Yun Yang , Naveen N. Narisetty

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in…

Machine Learning · Computer Science 2017-06-20 Lihong Li , Yu Lu , Dengyong Zhou

We present the first theoretical guarantees for differentially private online reinforcement learning (RL) with general function approximation, extending beyond prior work restricted to tabular and linear settings. Our approach combines a…

Machine Learning · Computer Science 2026-05-11 Yi He , Xingyu Zhou

Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When…

Machine Learning · Computer Science 2013-01-07 Tomas Kocka , Nevin Lianwen Zhang

On-line linear optimization on combinatorial action sets (d-dimensional actions) with bandit feedback, is known to have complexity in the order of the dimension of the problem. The exponential weighted strategy achieves the best known…

Machine Learning · Computer Science 2015-10-01 Shaona Ghosh , Adam Prugel-Bennett

We consider prediction with expert advice when the loss vectors are assumed to lie in a set described by the sum of atomic norm balls. We derive a regret bound for a general version of the online mirror descent (OMD) algorithm that uses a…

Machine Learning · Computer Science 2017-11-15 Siddharth Barman , Aditya Gopalan , Aadirupa Saha

We propose a framework which generalizes "decision making with structured observations" by allowing robust (i.e. multivalued) models. In this framework, each model associates each decision with a convex set of probability distributions over…

Machine Learning · Computer Science 2025-06-27 Alexander Appel , Vanessa Kosoy

Contextual bandit with linear reward functions is among one of the most extensively studied models in bandit and online learning research. Recently, there has been increasing interest in designing \emph{locally private} linear contextual…

Machine Learning · Statistics 2024-04-16 Jiachun Li , David Simchi-Levi , Yining Wang
‹ Prev 1 2 3 10 Next ›