Sample complexity of partition identification using multi-armed bandits
This work addresses a foundational problem in pure exploration for multi-armed bandits, with potential applications in domains like finance, though it appears incremental as it extends existing frameworks like best-arm identification.
The paper tackles the problem of identifying which partition a vector of probability distributions belongs to using multi-armed bandits, deriving sample complexity bounds and proposing algorithms that asymptotically match these bounds with decreasing error probability.
Given a vector of probability distributions, or arms, each of which can be sampled independently, we consider the problem of identifying the partition to which this vector belongs from a finitely partitioned universe of such vector of distributions. We study this as a pure exploration problem in multi armed bandit settings and develop sample complexity bounds on the total mean number of samples required for identifying the correct partition with high probability. This framework subsumes well studied problems such as finding the best arm or the best few arms. We consider distributions belonging to the single parameter exponential family and primarily consider partitions where the vector of means of arms lie either in a given set or its complement. The sets considered correspond to distributions where there exists a mean above a specified threshold, where the set is a half space and where either the set or its complement is a polytope, or more generally, a convex set. In these settings, we characterize the lower bounds on mean number of samples for each arm highlighting their dependence on the problem geometry. Further, inspired by the lower bounds, we propose algorithms that can match these bounds asymptotically with decreasing probability of error. Applications of this framework may be diverse. We briefly discuss one associated with finance.