On the Convergence of Continual Learning with Adaptive Methods

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Han, Seungyub, Kim, Yeongmo, Cho, Taehyun, Lee, Jungwoo
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917638778650624
author Han, Seungyub
Kim, Yeongmo
Cho, Taehyun
Lee, Jungwoo
author_facet Han, Seungyub
Kim, Yeongmo
Cho, Taehyun
Lee, Jungwoo
contents One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially, and the existing solutions have been driven by the conceptualization of the plasticity-stability dilemma. However, the convergence of continual learning for each sequential task is less studied so far. In this paper, we provide a convergence analysis of memory-based continual learning with stochastic gradient descent and empirical evidence that training current tasks causes the cumulative degradation of previous tasks. We propose an adaptive method for nonconvex continual learning (NCCL), which adjusts step sizes of both previous and current tasks with the gradients. The proposed method can achieve the same convergence rate as the SGD method when the catastrophic forgetting term which we define in the paper is suppressed at each iteration. Further, we demonstrate that the proposed algorithm improves the performance of continual learning over existing methods for several image classification tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2404_05555
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle On the Convergence of Continual Learning with Adaptive Methods
Han, Seungyub
Kim, Yeongmo
Cho, Taehyun
Lee, Jungwoo
Machine Learning
Artificial Intelligence
One of the objectives of continual learning is to prevent catastrophic forgetting in learning multiple tasks sequentially, and the existing solutions have been driven by the conceptualization of the plasticity-stability dilemma. However, the convergence of continual learning for each sequential task is less studied so far. In this paper, we provide a convergence analysis of memory-based continual learning with stochastic gradient descent and empirical evidence that training current tasks causes the cumulative degradation of previous tasks. We propose an adaptive method for nonconvex continual learning (NCCL), which adjusts step sizes of both previous and current tasks with the gradients. The proposed method can achieve the same convergence rate as the SGD method when the catastrophic forgetting term which we define in the paper is suppressed at each iteration. Further, we demonstrate that the proposed algorithm improves the performance of continual learning over existing methods for several image classification tasks.
title On the Convergence of Continual Learning with Adaptive Methods
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2404.05555