Quantile Multi-Armed Bandits with 1-bit Feedback

• URL: http://arxiv.org/abs/2502.06678v1
• Date: Mon, 10 Feb 2025 17:03:33 GMT
• Title: Quantile Multi-Armed Bandits with 1-bit Feedback
• Authors: Ivan Lau, Jonathan Scarlett,
• Abstract summary: We study a variant of best-arm identification involving elements of risk sensitivity and communication constraints. We propose an algorithm that utilizes noisy binary search as a subroutine, allowing the learner to estimate quantile rewards through 1-bit feedback.
• Score: 40.22079522118723
• License:
• Abstract: In this paper, we study a variant of best-arm identification involving elements of risk sensitivity and communication constraints. Specifically, the goal of the learner is to identify the arm with the highest quantile reward, while the communication from an agent (who observes rewards) and the learner (who chooses actions) is restricted to only one bit of feedback per arm pull. We propose an algorithm that utilizes noisy binary search as a subroutine, allowing the learner to estimate quantile rewards through 1-bit feedback. We derive an instance-dependent upper bound on the sample complexity of our algorithm and provide an algorithm-independent lower bound for specific instances, with the two matching to within logarithmic factors under mild conditions, or even to within constant factors in certain low error probability scaling regimes. The lower bound is applicable even in the absence of communication constraints, and thus we conclude that restricting to 1-bit feedback has a minimal impact on the scaling of the sample complexity.

Related papers

• Best Arm Identification with Minimal Regret [55.831935724659175]
  Best arm identification problem elegantly amalgamates regret minimization and BAI. Agent's goal is to identify the best arm with a prescribed confidence level. Double KL-UCB algorithm achieves optimality as the confidence level tends to zero.
  arXiv  Detail & Related papers  (2024-09-27T16:46:02Z)
• Best Arm Identification with Fixed Budget: A Large Deviation Perspective [54.305323903582845]
  We present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms. In particular, we present sred, a truly adaptive algorithm that can reject arms in it any round based on the observed empirical gaps between the rewards of various arms.
  arXiv  Detail & Related papers  (2023-12-19T13:17:43Z)
• Pure Exploration under Mediators' Feedback [63.56002444692792]
  Multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a reward. We consider the scenario in which the learner has access to a set of mediators, each of which selects the arms on the agent's behalf according to a and possibly unknown policy. We propose a sequential decision-making strategy for discovering the best arm under the assumption that the mediators' policies are known to the learner.
  arXiv  Detail & Related papers  (2023-08-29T18:18:21Z)
• Selective Sampling and Imitation Learning via Online Regression [17.73844193143454]
  We consider the problem of Imitation Learning (IL) by actively querying noisy expert for feedback. We provide an interactive algorithm for IL that uses selective sampling to actively query the noisy expert for feedback.
  arXiv  Detail & Related papers  (2023-07-11T03:32:20Z)
• Interactively Learning Preference Constraints in Linear Bandits [100.78514640066565]
  We study sequential decision-making with known rewards and unknown constraints. As an application, we consider learning constraints to represent human preferences in a driving simulation.
  arXiv  Detail & Related papers  (2022-06-10T17:52:58Z)
• Solving Multi-Arm Bandit Using a Few Bits of Communication [42.13277217013971]
  Multi-armed bandit (MAB) problem is an active learning framework that aims to select the best among a set of actions by sequentially observing rewards. We address the communication problem by optimizing the communication of rewards collected by distributed agents. We establish a generic reward quantization algorithm, QuBan, that can be applied on top of any (no-regret) MAB algorithm to form a new communication-efficient counterpart.
  arXiv  Detail & Related papers  (2021-11-11T06:23:16Z)
• Improved Algorithms for Agnostic Pool-based Active Classification [20.12178157010804]
  We consider active learning for binary classification in the agnostic pool-based setting. Our algorithm is superior to state of the art active learning algorithms on image classification datasets.
  arXiv  Detail & Related papers  (2021-05-13T18:24:30Z)
• Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme [16.1694012177079]
  We study the best-arm identification problem in multi-armed bandits with, potentially private rewards. The goal is to identify the arm with the highest quantile at a fixed, prescribed level. We show that our algorithm is $delta$-PAC and we characterize its sample complexity.
  arXiv  Detail & Related papers  (2020-06-11T20:23:43Z)
• The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime [52.38455827779212]
  We propose a novel technique for analyzing adaptive sampling called the em Simulator. We prove the first instance-based lower bounds the top-k problem which incorporate the appropriate log-factors. Our new analysis inspires a simple and near-optimal for the best-arm and top-k identification, the first em practical of its kind for the latter problem.
  arXiv  Detail & Related papers  (2017-02-16T23:42:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.