English

From inexact optimization to learning via gradient concentration

Machine Learning 2021-11-08 v3 Machine Learning Optimization and Control

Abstract

Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the error on future data (test error), for which the training data provides only partial information. In this view, the optimization problems that are practically feasible are based on inexact quantities that are stochastic in nature. In this paper, we show how probabilistic results, specifically gradient concentration, can be combined with results from inexact optimization to derive sharp test error guarantees. By considering unconstrained objectives we highlight the implicit regularization properties of optimization for learning.

Keywords

Cite

@article{arxiv.2106.05397,
  title  = {From inexact optimization to learning via gradient concentration},
  author = {Bernhard Stankewitz and Nicole Mücke and Lorenzo Rosasco},
  journal= {arXiv preprint arXiv:2106.05397},
  year   = {2021}
}
R2 v1 2026-06-24T03:02:00.769Z