Adaptive Estimation of Random Vectors with Bandit Feedback: A Mean-Squared Error Viewpoint

Sen, D and Prashanth, LA and Gopalan, A (2023) Adaptive Estimation of Random Vectors with Bandit Feedback: A Mean-Squared Error Viewpoint. In: UNSPECIFIED, pp. 180-181.

PDF 9th_Ind_con_con_2023pdf - Published Version Download (287kB)

Abstract

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 we 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. © 2023 IEEE.

Item Type:	Conference Proceedings
Publication:	2023 9th Indian Control Conference, ICC 2023 - Proceedings
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to authors.
Keywords:	Adaptive estimation; Bandit feedbacks; Concentration bounds; Estimation problem; Gaussians; Mean squared error; Mean squared error estimation; Minimax; Random vectors; Successive elimination algorithm, Mean square error
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	10 Apr 2024 06:09
Last Modified:	10 Apr 2024 06:09
URI:	https://eprints.iisc.ac.in/id/eprint/84512

Actions (login required)

View Item