paper-with-me

Papers

A Statistical Theory of Regularization-Based Continual Learning

2024-06-10 · Xuyang Zhao, Huiyuan Wang, Weiran Huang, Wei Lin

We provide a statistical analysis of regularization-based continual learning on a sequence of linear regression tasks, with emphasis on how different regularization terms affect the model performance. We first derive the convergence rate for the oracle estimator obtained as if all data were available simultaneously. Next, we consider a family of generalized $\ell_2$-regularization algorithms indexed by matrix-valued hyperparameters, which includes the minimum norm estimator and continual ridge regression as special cases. As more tasks are introduced, we derive an iterative update formula for the estimation error of generalized $\ell_2$-regularized estimators, from which we determine the hyperparameters resulting in the optimal algorithm. Interestingly, the choice of hyperparameters can effectively balance the trade-off between forward and backward knowledge transfer and adjust for data heterogeneity. Moreover, the estimation error of the optimal algorithm is derived explicitly, which is of the same order as that of the oracle estimator. In contrast, our lower bounds for the minimum norm estimator and continual ridge regression show their suboptimality. A byproduct of our theoretical analysis is the equivalence between early stopping and generalized $\ell_2$-regularization in continual learning, which may be of independent interest. Finally, we conduct experiments to complement our theory.

📄 PDF Abstract BibTeX arXiv:2406.06213

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningregressionTransfer Learning

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization

2025-04-05 · Haoran Li, Jingfeng Wu, Vladimir Braverman

We study the statistical performance of a continual learning problem with two linear regression tasks in a well-specified random design setting. We consider a structural regularization algorithm that incorporates a gener…

Continual Learning

CPR: Classifier-Projection Regularization for Continual Learning

2020-06-12 · ICLR 2021 1 · Sungmin Cha, Hsiang Hsu, Taebaek Hwang, Flavio P. Calmon 외

We propose a general, yet simple patch that can be applied to existing regularization-based continual learning methods called classifier-projection regularization (CPR). Inspired by both recent results on neural networks…

Continual Learning

Recovery Guarantees for Continual Learning of Dependent Tasks: Memory, Data-Dependent Regularization, and Data-Dependent Weights

2026-04-19 · Liangzu Peng, Uday Kiran Reddy Tadipatri, Ziqing Xu, Eric Eaton 외 arxiv

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 rema…

Knowledge DistillationContinual Learning

Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance

2025-11-03 · Rathin Chandra Shit arxiv

Catastrophic forgetting is one of the fundamental issues of continual learning because neural networks forget the tasks learned previously when trained on new tasks. The proposed framework is a new path-coordinated frame…

Continual Learning

Generalization in Machine Learning via Analytical Learning Theory

2018-02-21 · Kenji Kawaguchi, Yoshua Bengio, Vikas Verma, Leslie Pack Kaelbling

This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to outper…

BIG-bench Machine LearningDeep LearningLearning TheoryOne-Shot Learning+1