A deterministic gradient-based approach to avoid saddle points
Loss functions with a large number of saddle points are one of the major obstacles for training modern machine learning (ML) models efficiently. First-order methods such as gradient descent (GD) are usually the methods of choice for training ML models. However, these methods converge to saddle point...
Uložené v:
| Vydané v: | European journal of applied mathematics Ročník 34; číslo 4; s. 738 - 757 |
|---|---|
| Hlavní autori: | , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
Cambridge University Press
01.08.2023
|
| Predmet: | |
| ISSN: | 0956-7925, 1469-4425 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Shrnutí: | Loss functions with a large number of saddle points are one of the major obstacles for training modern machine learning (ML) models efficiently. First-order methods such as gradient descent (GD) are usually the methods of choice for training ML models. However, these methods converge to saddle points for certain choices of initial guesses. In this paper, we propose a modification of the recently proposed Laplacian smoothing gradient descent (LSGD) [Osher et al.,
arXiv:1806.06317
], called modified LSGD (mLSGD), and demonstrate its potential to avoid saddle points without sacrificing the convergence rate. Our analysis is based on the attraction region, formed by all starting points for which the considered numerical scheme converges to a saddle point. We investigate the attraction region’s dimension both analytically and numerically. For a canonical class of quadratic functions, we show that the dimension of the attraction region for mLSGD is
$\lfloor (n-1)/2\rfloor$
, and hence it is significantly smaller than that of GD whose dimension is
$n-1$
. |
|---|---|
| Bibliografia: | USDOE Office of Science (SC) SC0002722; SC0021142 |
| ISSN: | 0956-7925 1469-4425 |
| DOI: | 10.1017/S0956792522000316 |