Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification

11/02/2021
by   Clémence Réda, et al.
0

We study the problem of the identification of m arms with largest means under a fixed error rate δ (fixed-confidence Top-m identification), for misspecified linear bandit models. This problem is motivated by practical applications, especially in medicine and recommendation systems, where linear models are popular due to their simplicity and the existence of efficient algorithms, but in which data inevitably deviates from linearity. In this work, we first derive a tractable lower bound on the sample complexity of any δ-correct algorithm for the general Top-m identification problem. We show that knowing the scale of the deviation from linearity is necessary to exploit the structure of the problem. We then describe the first algorithm for this setting, which is both practical and adapts to the amount of misspecification. We derive an upper bound to its sample complexity which confirms this adaptivity and that matches the lower bound when δ → 0. Finally, we evaluate our algorithm on both synthetic and real-world data, showing competitive performance with respect to existing baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/13/2018

Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence

We consider the problem of near-optimal arm identification in the fixed ...
research
03/18/2021

Top-m identification for linear bandits

Motivated by an application to drug repurposing, we propose the first al...
research
09/05/2023

On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence

Best Arm Identification (BAI) problems are progressively used for data-s...
research
06/21/2020

An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits

This paper proposes near-optimal algorithms for the pure-exploration lin...
research
03/16/2023

On the Existence of a Complexity in Fixed Budget Bandit Identification

In fixed budget bandit identification, an algorithm sequentially observe...
research
02/20/2018

Adaptive Sampling for Coarse Ranking

We consider the problem of active coarse ranking, where the goal is to s...
research
07/13/2023

Nested Elimination: A Simple Algorithm for Best-Item Identification from Choice-Based Feedback

We study the problem of best-item identification from choice-based feedb...

Please sign up or login with your details

Forgot password? Click here to reset