Saved in:
Bibliographic Details
Main Authors: Luke, D. Russell, Schultze, Steffen, Grubmüller, Helmut
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.13454
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911763853737984
author Luke, D. Russell
Schultze, Steffen
Grubmüller, Helmut
author_facet Luke, D. Russell
Schultze, Steffen
Grubmüller, Helmut
contents We apply a recently developed framework for analyzing the convergence of stochastic algorithms to the general problem of large-scale nonconvex composite optimization more generally, and nonconvex likelihood maximization in particular. Our theory is demonstrated on a stochastic gradient descent algorithm for determining the electron density of a molecule from random samples of its scattering amplitude. Numerical results on an idealized synthetic example provide a proof of concept. This opens the door to a broad range of algorithmic possibilities and provides a basis for evaluating and comparing different strategies. While this case study is very specific, it shares a structure that transfers easily to many problems of current interest, particularly in machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13454
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Stochastic Algorithms for Large-Scale Composite Optimization: the Case of Single-Shot X-FEL Imaging
Luke, D. Russell
Schultze, Steffen
Grubmüller, Helmut
Optimization and Control
65C40, 90C26, 90C06
We apply a recently developed framework for analyzing the convergence of stochastic algorithms to the general problem of large-scale nonconvex composite optimization more generally, and nonconvex likelihood maximization in particular. Our theory is demonstrated on a stochastic gradient descent algorithm for determining the electron density of a molecule from random samples of its scattering amplitude. Numerical results on an idealized synthetic example provide a proof of concept. This opens the door to a broad range of algorithmic possibilities and provides a basis for evaluating and comparing different strategies. While this case study is very specific, it shares a structure that transfers easily to many problems of current interest, particularly in machine learning.
title Stochastic Algorithms for Large-Scale Composite Optimization: the Case of Single-Shot X-FEL Imaging
topic Optimization and Control
65C40, 90C26, 90C06
url https://arxiv.org/abs/2401.13454