Saved in:
Bibliographic Details
Main Authors: Yadav, Yajat, Mendoza, Patrick, Korrapati, Jathin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.17169
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909946628538368
author Yadav, Yajat
Mendoza, Patrick
Korrapati, Jathin
author_facet Yadav, Yajat
Mendoza, Patrick
Korrapati, Jathin
contents Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal convergence in learning tasks. To address this, we propose incorporating the natural gradient into OGD and present \textbf{ONG (Orthogonal Natural Gradient Descent)}. ONG preconditions each new task-specific gradient with an efficient EKFAC approximation of the inverse Fisher information matrix, yielding updates that follow the steepest descent direction under a Riemannian metric. To preserve performance on previously learned tasks, ONG projects these natural gradients onto the orthogonal complement of prior tasks' natural gradients. We provide an initial theoretical justification for this procedure, introduce the Orthogonal Natural Gradient Descent (ONG) algorithm, and present preliminary results on the Permuted and Rotated MNIST benchmarks. Our preliminary results, however, indicate that a naive combination of natural gradients and orthogonal projections has potential issues. This finding has motivated continued future work focused on robustly reconciling these geometric perspectives to develop a continual learning method, establishing a more rigorous theoretical foundation with formal convergence guarantees, and extending empirical validation to large-scale continual learning benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17169
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ONG: Orthogonal Natural Gradient Descent
Yadav, Yajat
Mendoza, Patrick
Korrapati, Jathin
Machine Learning
Artificial Intelligence
Orthogonal Gradient Descent (OGD) has emerged as a powerful method for continual learning. However, its Euclidean projections do not leverage the underlying information-geometric structure of the problem, which can lead to suboptimal convergence in learning tasks. To address this, we propose incorporating the natural gradient into OGD and present \textbf{ONG (Orthogonal Natural Gradient Descent)}. ONG preconditions each new task-specific gradient with an efficient EKFAC approximation of the inverse Fisher information matrix, yielding updates that follow the steepest descent direction under a Riemannian metric. To preserve performance on previously learned tasks, ONG projects these natural gradients onto the orthogonal complement of prior tasks' natural gradients. We provide an initial theoretical justification for this procedure, introduce the Orthogonal Natural Gradient Descent (ONG) algorithm, and present preliminary results on the Permuted and Rotated MNIST benchmarks. Our preliminary results, however, indicate that a naive combination of natural gradients and orthogonal projections has potential issues. This finding has motivated continued future work focused on robustly reconciling these geometric perspectives to develop a continual learning method, establishing a more rigorous theoretical foundation with formal convergence guarantees, and extending empirical validation to large-scale continual learning benchmarks.
title ONG: Orthogonal Natural Gradient Descent
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.17169