Saved in:
Bibliographic Details
Main Authors: Liao, Huafu, Mészáros, Alpár R., Mou, Chenchen, Zhou, Chao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.05185
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909652020625408
author Liao, Huafu
Mészáros, Alpár R.
Mou, Chenchen
Zhou, Chao
author_facet Liao, Huafu
Mészáros, Alpár R.
Mou, Chenchen
Zhou, Chao
contents This paper deals with a class of neural SDEs and studies the limiting behavior of the associated sampled optimal control problems as the sample size grows to infinity. The neural SDEs with $N$ samples can be linked to the $N$-particle systems with centralized control. We analyze the Hamilton-Jacobi-Bellman equation corresponding to the $N$-particle system and establish regularity results which are uniform in $N$. The uniform regularity estimates are obtained by the stochastic maximum principle and the analysis of a backward stochastic Riccati equation. Using these uniform regularity results, we show the convergence of the minima of the objective functionals and optimal parameters of the neural SDEs as the sample size $N$ tends to infinity. The limiting objects can be identified with suitable functions defined on the Wasserstein space of Borel probability measures. Furthermore, quantitative convergence rates are also obtained.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05185
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Convergence analysis of controlled particle systems arising in deep learning: from finite to infinite sample size
Liao, Huafu
Mészáros, Alpár R.
Mou, Chenchen
Zhou, Chao
Optimization and Control
Machine Learning
Probability
49N80, 65C35, 49L12, 62M45
This paper deals with a class of neural SDEs and studies the limiting behavior of the associated sampled optimal control problems as the sample size grows to infinity. The neural SDEs with $N$ samples can be linked to the $N$-particle systems with centralized control. We analyze the Hamilton-Jacobi-Bellman equation corresponding to the $N$-particle system and establish regularity results which are uniform in $N$. The uniform regularity estimates are obtained by the stochastic maximum principle and the analysis of a backward stochastic Riccati equation. Using these uniform regularity results, we show the convergence of the minima of the objective functionals and optimal parameters of the neural SDEs as the sample size $N$ tends to infinity. The limiting objects can be identified with suitable functions defined on the Wasserstein space of Borel probability measures. Furthermore, quantitative convergence rates are also obtained.
title Convergence analysis of controlled particle systems arising in deep learning: from finite to infinite sample size
topic Optimization and Control
Machine Learning
Probability
49N80, 65C35, 49L12, 62M45
url https://arxiv.org/abs/2404.05185