paper-with-me

홈 › Papers

Statistical Mechanical Analysis of Catastrophic Forgetting in Continual Learning with Teacher and Student Networks

2021-05-16 · Haruka Asanuma, Shiro Takagi, Yoshihiro Nagano, Yuki Yoshida, Yasuhiko Igarashi, Masato Okada

When a computational system continuously learns from an ever-changing environment, it rapidly forgets its past experiences. This phenomenon is called catastrophic forgetting. While a line of studies has been proposed with respect to avoiding catastrophic forgetting, most of the methods are based on intuitive insights into the phenomenon, and their performances have been evaluated by numerical experiments using benchmark datasets. Therefore, in this study, we provide the theoretical framework for analyzing catastrophic forgetting by using teacher-student learning. Teacher-student learning is a framework in which we introduce two neural networks: one neural network is a target function in supervised learning, and the other is a learning neural network. To analyze continual learning in the teacher-student framework, we introduce the similarity of the input distribution and the input-output relationship of the target functions as the similarity of tasks. In this theoretical framework, we also provide a qualitative understanding of how a single-layer linear learning neural network forgets tasks. Based on the analysis, we find that the network can avoid catastrophic forgetting when the similarity among input distributions is small and that of the input-output relationship of the target functions is large. The analysis also suggests that a system often exhibits a characteristic phenomenon called overshoot, which means that even if the learning network has once undergone catastrophic forgetting, it is possible that the network may perform reasonably well after further learning of the current task.

📄 PDF Abstract BibTeX arXiv:2105.07385

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Learning Curves for Continual Learning in Neural Networks: Self-Knowledge Transfer and Forgetting

2021-12-03 · ICLR 2022 4 · Ryo Karakida, Shotaro Akaho

Sequential training from task to task is becoming one of the major objects in deep learning applications such as continual learning and transfer learning. Nevertheless, it remains unclear under what conditions the traine…

Continual LearningTransfer Learning

Learning to Continually Learn with the Bayesian Principle

2024-05-29 · Soochan Lee, Hyeonseong Jeon, Jaehyeon Son, Gunhee Kim

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other…

Continual LearningMeta-Learning

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory

2024-09-26 · Francesco Mori, Stefano Sarao Mannelli, Francesca Mignacco

Artificial neural networks often struggle with catastrophic forgetting when learning multiple tasks sequentially, as training on new tasks degrades the performance on previously learned tasks. Recent theoretical work has…

Continual Learning

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

Statistical Theory of Multi-stage Newton Iteration Algorithm for Online Continual Learning

2025-08-10 · Xinjia Lu, Chuhan Wang, Qian Zhao, Lixing Zhu 외 arxiv

We focus on the critical challenge of handling non-stationary data streams in online continual learning environments, where constrained storage capacity prevents complete retention of historical data, leading to catastro…

Continual Learning