Saved in:
Bibliographic Details
Main Authors: Peng, Liangzu, Tadipatri, Uday Kiran Reddy, Xu, Ziqing, Eaton, Eric, Vidal, René
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.17578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913058178203648
author Peng, Liangzu
Tadipatri, Uday Kiran Reddy
Xu, Ziqing
Eaton, Eric
Vidal, René
author_facet Peng, Liangzu
Tadipatri, Uday Kiran Reddy
Xu, Ziqing
Eaton, Eric
Vidal, René
contents Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy. At the heart of developing CL theory lies the challenge that the data distribution varies across tasks, and we argue that properly addressing this challenge requires understanding this variation--dependency among tasks. To explicitly model task dependency, we consider nonlinear regression tasks and propose the assumption that these tasks are dependent in such a way that the data of the current task is a nonlinear transformation of previous data. With this model and under natural assumptions, we prove statistical recovery guarantees (more specifically, bounds on estimation errors) for several CL paradigms in practical use, including experience replay with data-independent regularization and data-independent weights that balance the losses of tasks, replay with data-dependent weights, and continual learning with data-dependent regularization (e.g., knowledge distillation). To the best of our knowledge, our bounds are informative in cases where prior work gives vacuous bounds.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17578
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
Peng, Liangzu
Tadipatri, Uday Kiran Reddy
Xu, Ziqing
Eaton, Eric
Vidal, René
Machine Learning
Statistics Theory
Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy. At the heart of developing CL theory lies the challenge that the data distribution varies across tasks, and we argue that properly addressing this challenge requires understanding this variation--dependency among tasks. To explicitly model task dependency, we consider nonlinear regression tasks and propose the assumption that these tasks are dependent in such a way that the data of the current task is a nonlinear transformation of previous data. With this model and under natural assumptions, we prove statistical recovery guarantees (more specifically, bounds on estimation errors) for several CL paradigms in practical use, including experience replay with data-independent regularization and data-independent weights that balance the losses of tasks, replay with data-dependent weights, and continual learning with data-dependent regularization (e.g., knowledge distillation). To the best of our knowledge, our bounds are informative in cases where prior work gives vacuous bounds.
title Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2604.17578