Mode Estimation with Partial Feedback
Machine Learning
2024-02-21 v1 Information Retrieval
Information Theory
Machine Learning
math.IT
Abstract
The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical frameworks. In this paper, we formalize core aspects of weakly supervised and active learning with a simple problem: the estimation of the mode of a distribution using partial feedback. We show how entropy coding allows for optimal information acquisition from partial feedback, develop coarse sufficient statistics for mode identification, and adapt bandit algorithms to our new setting. Finally, we combine those contributions into a statistically and computationally efficient solution to our problem.
Cite
@article{arxiv.2402.13079,
title = {Mode Estimation with Partial Feedback},
author = {Charles Arnal and Vivien Cabannes and Vianney Perchet},
journal= {arXiv preprint arXiv:2402.13079},
year = {2024}
}