Open Problem: Learning with Variational Objectives on Measures
Machine Learning
2023-11-17 v2 Machine Learning
Statistics Theory
Statistics Theory
Abstract
The theory of statistical learning has focused on variational objectives expressed on functions. In this note, we discuss motivations to write similar objectives on measures, in particular to discuss out-of-distribution generalization and weakly-supervised learning. It raises a natural question: can one cast usual statistical learning results to objectives expressed on measures? Does the resulting construction lead to new algorithms of practical interest?
Cite
@article{arxiv.2306.11928,
title = {Open Problem: Learning with Variational Objectives on Measures},
author = {Vivien Cabannes and Carles Domingo-Enrich},
journal= {arXiv preprint arXiv:2306.11928},
year = {2023}
}