English
Related papers

Related papers: On the Diminishing Returns of Width for Continual …

200 papers

Catastrophic forgetting has remained a significant challenge for efficient reinforcement learning for decades (Ring 1994, Rivest and Precup 2003). While recent works have proposed effective methods to mitigate this issue, they mainly focus…

Machine Learning · Computer Science 2025-09-24 Qingfeng Lan , Gautham Vasan , A. Rupam Mahmood

We study the neural-linear bandit model for solving sequential decision-making problems with high dimensional side information. Neural-linear bandits leverage the representation power of deep neural networks and combine it with efficient…

Machine Learning · Computer Science 2019-08-13 Tom Zahavy , Shie Mannor

A large body of research in continual learning is devoted to overcoming the catastrophic forgetting of neural networks by designing new algorithms that are robust to the distribution shifts. However, the majority of these works are strictly…

Machine Learning · Computer Science 2022-02-02 Seyed Iman Mirzadeh , Arslan Chaudhry , Dong Yin , Timothy Nguyen , Razvan Pascanu , Dilan Gorur , Mehrdad Farajtabar

In this paper, we propose a continual learning (CL) technique that is beneficial to sequential task learners by improving their retained accuracy and reducing catastrophic forgetting. The principal target of our approach is the automatic…

Machine Learning · Computer Science 2021-01-19 Ammar Shaker , Shujian Yu , Francesco Alesiani

Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced capabilities of Large Language Models (LLMs), they continue…

Machine Learning · Computer Science 2025-04-17 Gangwei Jiang , Caigao Jiang , Zhaoyi Li , Siqiao Xue , Jun Zhou , Linqi Song , Defu Lian , Ying Wei

We theoretically characterize gradient descent dynamics in deep linear networks trained at large width from random initialization and on large quantities of random data. Our theory captures the ``wider is better" effect of…

Machine Learning · Computer Science 2025-06-17 Blake Bordelon , Cengiz Pehlevan

Deep residual networks (ResNets) have demonstrated better generalization performance than deep feedforward networks (FFNets). However, the theory behind such a phenomenon is still largely unknown. This paper studies this fundamental problem…

Machine Learning · Computer Science 2020-12-23 Kaixuan Huang , Yuqing Wang , Molei Tao , Tuo Zhao

One of the main motivations of studying continual learning is that the problem setting allows a model to accrue knowledge from past tasks to learn new tasks more efficiently. However, recent studies suggest that the key metric that…

Machine Learning · Computer Science 2023-03-16 Jiefeng Chen , Timothy Nguyen , Dilan Gorur , Arslan Chaudhry

The magnitude of parameter updates are considered a key factor in continual learning. However, most existing studies focus on designing diverse update strategies, while a theoretical understanding of the underlying mechanisms remains…

Machine Learning · Computer Science 2026-02-25 JinLi He , Liang Bai , Xian Yang

Deep Learning models have achieved remarkable performance in tasks such as image classification or generation, often surpassing human accuracy. However, they can struggle to learn new tasks and update their knowledge without access to…

Machine Learning · Computer Science 2023-12-19 Everton L. Aleixo , Juan G. Colonna , Marco Cristo , Everlandio Fernandes

This work theoretically studies stochastic neural networks, a main type of neural network in use. We prove that as the width of an optimized stochastic neural network tends to infinity, its predictive variance on the training set decreases…

Machine Learning · Computer Science 2022-05-25 Liu Ziyin , Hanlin Zhang , Xiangming Meng , Yuting Lu , Eric Xing , Masahito Ueda

Deep neural networks have achieved remarkable success in practice, yet a mechanistic understanding of how features evolve during training remains incomplete, especially in the large-depth limit. For ResNets under depth-$\mu$P scaling, prior…

Machine Learning · Computer Science 2026-05-28 Zihan Yao , Ruoyu Wu , Tianxiang Gao

Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine…

Machine Learning · Computer Science 2020-03-05 Shawn Beaulieu , Lapo Frati , Thomas Miconi , Joel Lehman , Kenneth O. Stanley , Jeff Clune , Nick Cheney

Catastrophic forgetting (CF) is a phenomenon that occurs in machine learning when a model forgets previously learned information while acquiring new knowledge for achieving a satisfactory performance in downstream tasks. As large language…

Computation and Language · Computer Science 2025-01-07 Yun Luo , Zhen Yang , Fandong Meng , Yafu Li , Jie Zhou , Yue Zhang

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 David Berga , Marc Masana , Joost Van de Weijer

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…

Machine Learning · Computer Science 2023-05-30 Ketaki Joshi , Raghavendra Pradyumna Pothukuchi , Andre Wibisono , Abhishek Bhattacharjee

Continual learning can incrementally absorb new concepts without interfering with previously learned knowledge. Motivated by the characteristics of neural networks, in which information is stored in weights on connections, we investigated…

Machine Learning · Computer Science 2023-06-21 Depeng Li , Tianqi Wang , Bingrong Xu , Kenji Kawaguchi , Zhigang Zeng , Ponnuthurai Nagaratnam Suganthan

In practice, multi-task learning (through learning features shared among tasks) is an essential property of deep neural networks (NNs). While infinite-width limits of NNs can provide good intuition for their generalization behavior, the…

Machine Learning · Computer Science 2022-10-21 Jakob Heiss , Josef Teichmann , Hanna Wutte

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop…

Machine Learning · Computer Science 2025-12-19 Hesham G. Moussa , Aroosa Hameed , Arashmid Akhavain