paper-with-me

홈 › Papers

Neural Contextual Bandits without Regret

2021-07-07 · Parnian Kassraie, Andreas Krause

Contextual bandits are a rich model for sequential decision making given side information, with important applications, e.g., in recommender systems. We propose novel algorithms for contextual bandits harnessing neural networks to approximate the unknown reward function. We resolve the open problem of proving sublinear regret bounds in this setting for general context sequences, considering both fully-connected and convolutional networks. To this end, we first analyze NTK-UCB, a kernelized bandit optimization algorithm employing the Neural Tangent Kernel (NTK), and bound its regret in terms of the NTK maximum information gain $\gamma_T$, a complexity parameter capturing the difficulty of learning. Our bounds on $\gamma_T$ for the NTK may be of independent interest. We then introduce our neural network based algorithm NN-UCB, and show that its regret closely tracks that of NTK-UCB. Under broad non-parametric assumptions about the reward function, our approach converges to the optimal policy at a $\tilde{\mathcal{O}}(T^{-1/2d})$ rate, where $d$ is the dimension of the context.

📄 PDF Abstract BibTeX arXiv:2107.03144

Code (1)

pkassraie/NNUCB 공식 구현 jax

Tasks

Decision MakingMulti-Armed BanditsRecommendation SystemsSequential Decision Making

Methods 이 논문이 사용한 방법론

NTK 설명 없음

Similar Papers 제목 키워드 기반

A conversion theorem and minimax optimality for continuum contextual bandits

2024-06-09 · Arya Akhavan, Karim Lounici, Massimiliano Pontil, Alexandre B. Tsybakov

We study the contextual continuum bandits problem, where the learner sequentially receives a side information vector and has to choose an action in a convex set, minimizing a function associated with the context. The goa…

Multi-Armed Bandits

Simple Regret Minimization for Contextual Bandits

2018-10-17 · Aniket Anand Deshmukh, Srinagesh Sharma, James W. Cutler, Mark Moldwin 외

There are two variants of the classical multi-armed bandit (MAB) problem that have received considerable attention from machine learning researchers in recent years: contextual bandits and simple regret minimization. Con…

Multi-Armed Bandits

Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards

2023-04-26 · Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund

In this work, we study the performance of the Thompson Sampling algorithm for Contextual Bandit problems based on the framework introduced by Neu et al. and their concept of lifted information ratio. First, we prove a co…

Multi-Armed BanditsThompson Sampling

Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

2019-09-05 · Yichun Hu, Nathan Kallus, Xiaojie Mao

We study a nonparametric contextual bandit problem where the expected reward functions belong to a H\"older class with smoothness parameter $\beta$. We show how this interpolates between two extremes that were previously…

Multi-Armed Bandits

Breaking the $\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits

2022-05-19 · Avishek Ghosh, Abishek Sankararaman

We prove an instance independent (poly) logarithmic regret for stochastic contextual bandits with linear payoff. Previously, in \cite{chu2011contextual}, a lower bound of $\mathcal{O}(\sqrt{T})$ is shown for the contextu…

Multi-Armed Banditsparameter estimation