On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Godichon-Baggioni, Antoine, Werge, Nicklas
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911768656216064
author Godichon-Baggioni, Antoine
Werge, Nicklas
author_facet Godichon-Baggioni, Antoine
Werge, Nicklas
contents Stochastic optimization methods encounter new challenges in the realm of streaming, characterized by a continuous flow of large, high-dimensional data. While first-order methods, like stochastic gradient descent, are the natural choice, they often struggle with ill-conditioned problems. In contrast, second-order methods, such as Newton's methods, offer a potential solution, but their computational demands render them impractical. This paper introduces adaptive stochastic optimization methods that bridge the gap between addressing ill-conditioned problems while functioning in a streaming context. Notably, we present an adaptive inversion-free Newton's method with a computational complexity matching that of first-order methods, $\mathcal{O}(dN)$, where $d$ represents the number of dimensions/features, and $N$ the number of data. Theoretical analysis confirms their asymptotic efficiency, and empirical evidence demonstrates their effectiveness, especially in scenarios involving complex covariance structures and challenging initializations. In particular, our adaptive Newton's methods outperform existing methods, while maintaining favorable computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2311_17753
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations
Godichon-Baggioni, Antoine
Werge, Nicklas
Statistics Theory
Stochastic optimization methods encounter new challenges in the realm of streaming, characterized by a continuous flow of large, high-dimensional data. While first-order methods, like stochastic gradient descent, are the natural choice, they often struggle with ill-conditioned problems. In contrast, second-order methods, such as Newton's methods, offer a potential solution, but their computational demands render them impractical. This paper introduces adaptive stochastic optimization methods that bridge the gap between addressing ill-conditioned problems while functioning in a streaming context. Notably, we present an adaptive inversion-free Newton's method with a computational complexity matching that of first-order methods, $\mathcal{O}(dN)$, where $d$ represents the number of dimensions/features, and $N$ the number of data. Theoretical analysis confirms their asymptotic efficiency, and empirical evidence demonstrates their effectiveness, especially in scenarios involving complex covariance structures and challenging initializations. In particular, our adaptive Newton's methods outperform existing methods, while maintaining favorable computational efficiency.
title On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations
topic Statistics Theory
url https://arxiv.org/abs/2311.17753