paper-with-me

홈 › Papers

Adaptive Estimation of Random Vectors with Bandit Feedback: A mean-squared error viewpoint

2022-03-31 · Dipayan Sen, L. A. Prashanth, Aditya Gopalan

We consider the problem of sequentially learning to estimate, in the mean squared error (MSE) sense, a Gaussian $K$-vector of unknown covariance by observing only $m < K$ of its entries in each round. We first establish a concentration bound for MSE estimation. We then frame the estimation problem with bandit feedback, and propose a variant of the successive elimination algorithm. We also derive a minimax lower bound to understand the fundamental limit on the sample complexity of this problem.

📄 PDF Abstract BibTeX arXiv:2203.16810

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs

2024-02-12 · Yuval Filmus, Steve Hanneke, Idan Mehalel, Shay Moran

Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the…

Classification

Contextual Linear Optimization with Bandit Feedback

2024-05-26 · Yichun Hu, Nathan Kallus, Xiaojie Mao, Yanchen Wu

Contextual linear optimization (CLO) uses predictive contextual features to reduce uncertainty in random cost coefficients and thereby improve average-cost performance. An example is the stochastic shortest path problem …

Bandits with Switching Costs: T^{2/3} Regret

2013-10-11 · Ofer Dekel, Jian Ding, Tomer Koren, Yuval Peres

We study the adversarial multi-armed bandit problem in a setting where the player incurs a unit cost each time he switches actions. We prove that the player's $T$-round minimax regret in this setting is $\widetilde{\Thet…

Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback

2026-05-01 · Shradha Sharma, Swapnil Dhamal, Shweta Jain arxiv

We study meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback, where a learner selects at most $K$ arms per time step and observes only the noisy aggregate reward of the selected …

Multi-Armed BanditsFederated Learning

Adaptive Combinatorial Experimental Design: Pareto Optimality for Decision-Making and Inference

2026-02-27 · Hongrui Xie, Junyu Cao, Kan Xu arxiv

In this paper, we provide the first investigation into adaptive combinatorial experimental design, focusing on the trade-off between regret minimization and statistical power in combinatorial multi-armed bandits (CMAB). …

Multi-Armed Bandits