Selective Sampling for Online Best-arm Identification

10/28/2021
βˆ™
by   Romain Camilleri, et al.
βˆ™
0
βˆ™

This work considers the problem of selective-sampling for best-arm identification. Given a set of potential options π’΅βŠ‚β„^d, a learner aims to compute with probability greater than 1-Ξ΄, max_zβˆˆπ’΅ z^⊀θ_βˆ— where ΞΈ_βˆ— is unknown. At each time step, a potential measurement x_tβˆˆπ’³βŠ‚β„^d is drawn IID and the learner can either choose to take the measurement, in which case they observe a noisy measurement of x^⊀θ_βˆ—, or to abstain from taking the measurement and wait for a potentially more informative point to arrive in the stream. Hence the learner faces a fundamental trade-off between the number of labeled samples they take and when they have collected enough evidence to declare the best arm and stop sampling. The main results of this work precisely characterize this trade-off between labeled samples and stopping time and provide an algorithm that nearly-optimally achieves the minimal label complexity given a desired stopping time. In addition, we show that the optimal decision rule has a simple geometric form based on deciding whether a point is in an ellipse or not. Finally, our framework is general enough to capture binary classification improving upon previous works.

READ FULL TEXT
research
βˆ™ 05/10/2023

Best Arm Identification in Bandits with Limited Precision Sampling

We study best arm identification in a variant of the multi-armed bandit ...
research
βˆ™ 09/01/2023

Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms

This paper considers a stochastic multi-armed bandit (MAB) problem with ...
research
βˆ™ 09/29/2021

Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification

We consider a variant of online binary classification where a learner se...
research
βˆ™ 10/03/2022

Dealing with Unknown Variances in Best-Arm Identification

The problem of identifying the best arm among a collection of items havi...
research
βˆ™ 10/24/2019

Fixed-Confidence Guarantees for Bayesian Best-Arm Identification

We investigate and provide new insights on the sampling rule called Top-...
research
βˆ™ 05/29/2017

Improving the Expected Improvement Algorithm

The expected improvement (EI) algorithm is a popular strategy for inform...
research
βˆ™ 04/14/2022

Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach

In sliced networks, the shared tenancy of slices requires adaptive admis...

Please sign up or login with your details

Forgot password? Click here to reset