Salvato in:
Dettagli Bibliografici
Autori principali: Cheon, Jeonghwan, Bae, Jaehyuk, Paik, Se-Bum
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.20892
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910970469679104
author Cheon, Jeonghwan
Bae, Jaehyuk
Paik, Se-Bum
author_facet Cheon, Jeonghwan
Bae, Jaehyuk
Paik, Se-Bum
contents Backpropagation is the cornerstone of deep learning, but its reliance on symmetric weight transport and global synchronization makes it computationally expensive and biologically implausible. Feedback alignment offers a promising alternative by approximating error gradients through fixed random feedback, thereby avoiding symmetric weight transport. However, this approach often struggles with poor learning performance and instability, especially in deep networks. Here, we show that a one-time soft alignment between forward and feedback weights at initialization enables deep networks to achieve performance comparable to backpropagation, without requiring weight transport during learning. This simple initialization condition guides stable error minimization in the loss landscape, improving network trainability. Spectral analyses further reveal that initial alignment promotes smoother gradient flow and convergence to flatter minima, resulting in better generalization and robustness. Notably, we also find that allowing moderate deviations from exact weight symmetry can improve adversarial robustness compared to standard backpropagation. These findings demonstrate that a simple initialization strategy can enable effective learning in deep networks in a biologically plausible and resource-efficient manner.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20892
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle One-Time Soft Alignment Enables Resilient Learning without Weight Transport
Cheon, Jeonghwan
Bae, Jaehyuk
Paik, Se-Bum
Machine Learning
Backpropagation is the cornerstone of deep learning, but its reliance on symmetric weight transport and global synchronization makes it computationally expensive and biologically implausible. Feedback alignment offers a promising alternative by approximating error gradients through fixed random feedback, thereby avoiding symmetric weight transport. However, this approach often struggles with poor learning performance and instability, especially in deep networks. Here, we show that a one-time soft alignment between forward and feedback weights at initialization enables deep networks to achieve performance comparable to backpropagation, without requiring weight transport during learning. This simple initialization condition guides stable error minimization in the loss landscape, improving network trainability. Spectral analyses further reveal that initial alignment promotes smoother gradient flow and convergence to flatter minima, resulting in better generalization and robustness. Notably, we also find that allowing moderate deviations from exact weight symmetry can improve adversarial robustness compared to standard backpropagation. These findings demonstrate that a simple initialization strategy can enable effective learning in deep networks in a biologically plausible and resource-efficient manner.
title One-Time Soft Alignment Enables Resilient Learning without Weight Transport
topic Machine Learning
url https://arxiv.org/abs/2505.20892