Langevin dynamics based algorithm e-THεO POULA for stochastic optimization problems with discontinuous stochastic gradient
Dong-Young Lim, Ariel Neufeld, Sotirios Sabanis, Ying Zhang
| Year of publication: |
2025
|
|---|---|
| Authors: | Lim, Dong-Young ; Neufeld, Ariel ; Sabanis, Sotirios ; Zhang, Ying |
| Published in: |
Mathematics of operations research. - Hanover, Md. : INFORMS, ISSN 1526-5471, ZDB-ID 2004273-5. - Vol. 50.2025, 3, p. 2333-2374
|
| Subject: | artificial neural networks | discontinuous stochastic gradient | Langevin dynamics based algorithm | nonasymptotic convergence bound | nonconvex stochastic optimization | ReLU activation function | superlinearly growing coefficients | taming technique | Theorie | Theory | Stochastischer Prozess | Stochastic process | Mathematische Optimierung | Mathematical programming | Neuronale Netze | Neural networks | Algorithmus | Algorithm |
| Type of publication: | Article |
|---|---|
| Type of publication (narrower categories): | Aufsatz in Zeitschrift ; Article in journal |
| Language: | English |
| Other identifiers: | 10.1287/moor.2022.0307 [DOI] |
| Source: | ECONIS - Online Catalogue of the ZBW |
Persistent link: https://www.econbiz.de/10015444758