SHARP GLOBAL CONVERGENCE GUARANTEES FOR ITERATIVE NONCONVEX OPTIMIZATION WITH RANDOM DATA

Kabir Aladin Chandrasekher, Ashwin Pananjady, Christos Thrampoulidis

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

We consider a general class of regression models with normally distributed covariates, and the associated nonconvex problem of fitting these models from data. We develop a general recipe for analyzing the convergence of iterative algorithms for this task from a random initialization. In particular, provided each iteration can be written as the solution to a convex optimization problem satisfying some natural conditions, we leverage Gaussian comparison theorems to derive a deterministic sequence that provides sharp upper and lower bounds on the error of the algorithm with sample splitting. Crucially, this deterministic sequence accurately captures both the convergence rate of the algorithm and the eventual error floor in the finite-sample regime, and is distinct from the commonly used “population” sequence that results from taking the infinite-sample limit. We apply our general framework to derive several concrete consequences for parameter estimation in popular statistical models including phase retrieval and mixtures of regressions. Provided the sample size scales near linearly in the dimension, we show sharp global convergence rates for both higher-order algorithms based on alternating updates and first-order algorithms based on subgradient descent. These corollaries, in turn, reveal multiple nonstandard phenomena that are then corroborated by extensive numerical experiments.
Original languageEnglish (US)
Pages (from-to)179-210
Number of pages32
JournalAnnals of Statistics
Volume51
Issue number1
DOIs
StatePublished - Feb 1 2023
Externally publishedYes

Bibliographical note

KAUST Repository Item: Exported on 2023-05-24
Acknowledgements: KAC was supported in part by a National Science Foundation Graduate Research Fellowship and the Sony Stanford Graduate Fellowship. AP was supported in part by a research fellowship from the Simons Institute and National Science Foundation Grant CCF-2107455. CT was supported in part by the National Science Foundation Grant CCF-2009030, by an NSERC Discovery Grant and by a research grant from KAUST.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Fingerprint

Dive into the research topics of 'SHARP GLOBAL CONVERGENCE GUARANTEES FOR ITERATIVE NONCONVEX OPTIMIZATION WITH RANDOM DATA'. Together they form a unique fingerprint.

Cite this