A Unified Model and Dimension for Interactive Estimation

Published: 21 Sept 2023, Last Modified: 22 Jan 2024NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Interactive learning, bandits, statistical queries
Abstract: We study an abstract framework for interactive learning called interactive estimation in which the goal is to estimate a target from its ``similarity'' to points queried by the learner. We introduce a combinatorial measure called Dissimilarity dimension which largely captures learnability in our model. We present a simple, general, and broadly-applicable algorithm, for which we obtain both regret and PAC generalization bounds that are polynomial in the new dimension. We show that our framework subsumes and thereby unifies two classic learning models: statistical-query learning and structured bandits. We also delineate how the Dissimilarity dimension is related to well-known parameters for both frameworks, in some cases yielding significantly improved analyses.
Supplementary Material: zip
Submission Number: 13737