CSG: A stochastic gradient method for a wide class of optimization problems appearing in a machine learning or data-driven context
A recent article introduced thecontinuous stochastic gradient method (CSG) for the efficient solution of a class of stochastic optimization problems. While the applicability of known stochastic gradient type methods is typically limited to expected risk functions, no such limitation exists for CSG....
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | A recent article introduced thecontinuous stochastic gradient method (CSG)
for the efficient solution of a class of stochastic optimization problems.
While the applicability of known stochastic gradient type methods is typically
limited to expected risk functions, no such limitation exists for CSG. This
advantage stems from the computation of design dependent integration weights,
allowing for optimal usage of available information and therefore stronger
convergence properties. However, the nature of the formula used for these
integration weights essentially limited the practical applicability of this
method to problems in which stochasticity enters via a low-dimensional and
sufficiently simple probability distribution. In this paper we significantly
extend the scope of the CSG method by presenting alternative ways to calculate
the integration weights. A full convergence analysis for this new variant of
the CSG method is presented and its efficiency is demonstrated in comparison to
more classical stochastic gradient methods by means of a number of problem
classes relevant to stochastic optimization and machine learning. |
---|---|
DOI: | 10.48550/arxiv.2111.07322 |