On the Existence of a Complexity in Fixed Budget Bandit Identification
R\'emy Degenne

TL;DR
This paper investigates the fundamental limits of fixed budget bandit identification, revealing that for some tasks, no single algorithm can achieve the optimal error decay rate across all problem instances.
Contribution
It introduces the concept of complexity as a lower bound on error probability and shows it is determined by the best non-adaptive sampling strategy, highlighting limitations in fixed budget identification.
Findings
Existence of complexity depends on the problem
No universal optimal algorithm for Bernoulli best arm with two arms
Complexity is linked to non-adaptive sampling procedures
Abstract
In fixed budget bandit identification, an algorithm sequentially observes samples from several distributions up to a given final time. It then answers a query about the set of distributions. A good algorithm will have a small probability of error. While that probability decreases exponentially with the final time, the best attainable rate is not known precisely for most identification tasks. We show that if a fixed budget task admits a complexity, defined as a lower bound on the probability of error which is attained by the same algorithm on all bandit problems, then that complexity is determined by the best non-adaptive sampling procedure for that problem. We show that there is no such complexity for several fixed budget identification tasks including Bernoulli best arm identification with two arms: there is no single algorithm that attains everywhere the best possible rate.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Algorithms · Advanced Bandit Algorithms Research · Auction Theory and Applications
