Work

Instance-Dependent Regret Analysis of Kernelized Bandits

Year: 2022

Type: preprint

Abstract: We study the kernelized bandit problem, that involves designing an adaptive strategy for querying a noisy zeroth-order-oracle to efficiently learn about the optimizer of an unknown function $f$ with a norm bounded by $M

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2203.06297

Authors: Shekhar, Shubhanshu, Javidi, Tara

Institutions: Central Michigan University, Chiang Mai University, Carnegie Mellon University, University of California San Diego

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

OpenAlex ID: W4221151968

Cites:

Cited by:

Related to: 10