Structured Prediction in Online Learning
Machine Learning
2024-06-19 v1 Statistics Theory
Machine Learning
Statistics Theory
Abstract
We study a theoretical and algorithmic framework for structured prediction in the online learning setting. The problem of structured prediction, i.e. estimating function where the output space lacks a vectorial structure, is well studied in the literature of supervised statistical learning. We show that our algorithm is a generalisation of optimal algorithms from the supervised learning setting, and achieves the same excess risk upper bound also when data are not i.i.d. Moreover, we consider a second algorithm designed especially for non-stationary data distributions, including adversarial data. We bound its stochastic regret in function of the variation of the data distributions.
Cite
@article{arxiv.2406.12366,
title = {Structured Prediction in Online Learning},
author = {Pierre Boudart and Alessandro Rudi and Pierre Gaillard},
journal= {arXiv preprint arXiv:2406.12366},
year = {2024}
}
Comments
29 pages