paper-with-me

홈 › Papers

Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits

2019-03-30 · Yingkai Li, Yining Wang, Yuan Zhou

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected regret is $\Omega(\sqrt{dT (\log T) (\log n)})$ for every algorithm, and (2) introduce a Variable-Confidence-Level (VCL) SupLinUCB algorithm whose regret matches the lower bound up to iterated logarithmic factors. Our algorithmic result saves two $\sqrt{\log T}$ factors from previous analysis, and our information-theoretical lower bound also improves previous results by one $\sqrt{\log T}$ factor, revealing a regret scaling quite different from classical multi-armed bandits in which no logarithmic $T$ term is present in minimax regret. Our proof techniques include variable confidence levels and a careful analysis of layer sizes of SupLinUCB on the upper bound side, and delicately constructed adversarial sequences showing the tightness of elliptical potential lemmas on the lower bound side.

📄 PDF Abstract BibTeX arXiv:1904.00242

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

Similar Papers 제목 키워드 기반

Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model

2021-05-28 · NeurIPS 2021 12 · Bingyan Wang, Yuling Yan, Jianqing Fan

The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $\mathcal{S}$ and the action space $\mathcal{A}$ are both finite, to obtain a nearly optima…

Q-Learningreinforcement-learningReinforcement Learning (RL)

Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization

2022-10-31 · Chris Junchi Li, Angela Yuan, Gauthier Gidel, Quanquan Gu 외

We propose a new first-order optimization algorithm -- AcceleratedGradient-OptimisticGradient (AG-OG) Descent Ascent -- for separable convex-concave minimax optimization. The main idea of our algorithm is to carefully le…

On the Suboptimality of Thompson Sampling in High Dimensions

2021-02-10 · NeurIPS 2021 12 · Raymond Zhang, Richard Combes

In this paper we consider Thompson Sampling (TS) for combinatorial semi-bandits. We demonstrate that, perhaps surprisingly, TS is sub-optimal for this problem in the sense that its regret scales exponentially in the ambi…

Thompson SamplingVocal Bursts Intensity Prediction

Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret

2022-11-21 · Gautam Goel, Naman Agarwal, Karan Singh, Elad Hazan

We consider the fundamental problem of online control of a linear dynamical system from two different viewpoints: regret minimization and competitive analysis. We prove that the optimal competitive policy is well-approxi…

Bandit algorithms to emulate human decision making using probabilistic distortions

2016-11-30 · Ravi Kumar Kolla, Prashanth L. A., Aditya Gopalan, Krishna Jagannathan 외

Motivated by models of human decision making proposed to explain commonly observed deviations from conventional expected value preferences, we formulate two stochastic multi-armed bandit problems with distorted probabili…

Decision MakingMulti-Armed Bandits