On the Role of Initialization on the Implicit Bias in Deep Linear Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gruber, Oria, Avron, Haim
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914666325737472
author Gruber, Oria
Avron, Haim
author_facet Gruber, Oria
Avron, Haim
contents Despite Deep Learning's (DL) empirical success, our theoretical understanding of its efficacy remains limited. One notable paradox is that while conventional wisdom discourages perfect data fitting, deep neural networks are designed to do just that, yet they generalize effectively. This study focuses on exploring this phenomenon attributed to the implicit bias at play. Various sources of implicit bias have been identified, such as step size, weight initialization, optimization algorithm, and number of parameters. In this work, we focus on investigating the implicit bias originating from weight initialization. To this end, we examine the problem of solving underdetermined linear systems in various contexts, scrutinizing the impact of initialization on the implicit regularization when using deep networks to solve such systems. Our findings elucidate the role of initialization in the optimization and generalization paradoxes, contributing to a more comprehensive understanding of DL's performance characteristics.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02454
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Role of Initialization on the Implicit Bias in Deep Linear Networks
Gruber, Oria
Avron, Haim
Machine Learning
Numerical Analysis
Despite Deep Learning's (DL) empirical success, our theoretical understanding of its efficacy remains limited. One notable paradox is that while conventional wisdom discourages perfect data fitting, deep neural networks are designed to do just that, yet they generalize effectively. This study focuses on exploring this phenomenon attributed to the implicit bias at play. Various sources of implicit bias have been identified, such as step size, weight initialization, optimization algorithm, and number of parameters. In this work, we focus on investigating the implicit bias originating from weight initialization. To this end, we examine the problem of solving underdetermined linear systems in various contexts, scrutinizing the impact of initialization on the implicit regularization when using deep networks to solve such systems. Our findings elucidate the role of initialization in the optimization and generalization paradoxes, contributing to a more comprehensive understanding of DL's performance characteristics.
title On the Role of Initialization on the Implicit Bias in Deep Linear Networks
topic Machine Learning
Numerical Analysis
url https://arxiv.org/abs/2402.02454