English
Related papers

Related papers: Understanding Forgetting in Continual Learning wit…

200 papers

Deep learning has proved to be a successful paradigm for solving many challenges in machine learning. However, deep neural networks fail when trained sequentially on multiple tasks, a shortcoming known as catastrophic forgetting in the…

Machine Learning · Computer Science 2023-10-03 Giulia Lanzillotta , Sidak Pal Singh , Benjamin F. Grewe , Thomas Hofmann

Catastrophic forgetting is a problem faced by many machine learning models and algorithms. When trained on one task, then trained on a second task, many machine learning models "forget" how to perform the first task. This is widely believed…

Machine Learning · Statistics 2015-03-05 Ian J. Goodfellow , Mehdi Mirza , Da Xiao , Aaron Courville , Yoshua Bengio

Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference…

Machine Learning · Computer Science 2022-10-04 Xiaohan Zou , Tong Lin

Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…

Computation and Language · Computer Science 2024-10-23 Chonghua Liao , Ruobing Xie , Xingwu Sun , Haowen Sun , Zhanhui Kang

Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…

Artificial Intelligence · Computer Science 2020-02-11 Giacomo Spigler

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due…

Neural and Evolutionary Computing · Computer Science 2015-04-20 Tomas Mikolov , Armand Joulin , Sumit Chopra , Michael Mathieu , Marc'Aurelio Ranzato

Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to…

Machine Learning · Computer Science 2020-09-30 Amanda Rios , Laurent Itti

Continual/lifelong learning from a non-stationary input data stream is a cornerstone of intelligence. Despite their phenomenal performance in a wide variety of applications, deep neural networks are prone to forgetting their previously…

Machine Learning · Computer Science 2022-07-11 Ali Abbasi , Parsa Nooralinejad , Vladimir Braverman , Hamed Pirsiavash , Soheil Kolouri

We study how different output layer parameterizations of a deep neural network affects learning and forgetting in continual learning settings. The following three effects can cause catastrophic forgetting in the output layer: (1) weights…

Machine Learning · Computer Science 2022-08-19 Timothée Lesort , Thomas George , Irina Rish

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Machine Learning · Computer Science 2019-10-23 Dongmin Park , Seokil Hong , Bohyung Han , Kyoung Mu Lee

A catastrophic forgetting problem makes deep neural networks forget the previously learned information, when learning data collected in new environments, such as by different sensors or in different light conditions. This paper presents a…

Machine Learning · Computer Science 2016-07-04 Heechul Jung , Jeongwoo Ju , Minju Jung , Junmo Kim

Stochastic Gradient Descent (SGD) and its variants are almost universally used to train neural networks and to fit a variety of other parametric models. An important hyperparameter in this context is the batch size, which determines how…

Optimization and Control · Mathematics 2023-12-05 Stefan Perko

Recent advancements in large language models (LLMs) reveal a perplexing phenomenon in continual learning: despite extensive training, models experience significant performance declines, raising questions about task alignment and underlying…

Machine Learning · Computer Science 2025-01-24 Junhao Zheng , Xidi Cai , Shengjie Qiu , Qianli Ma

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

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of…

Machine Learning · Computer Science 2023-06-08 Maksym Andriushchenko , Aditya Varre , Loucas Pillaud-Vivien , Nicolas Flammarion

Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophically forgetting previous ones. We propose a model that…

Machine Learning · Computer Science 2020-12-18 Craig Atkinson , Brendan McCane , Lech Szymanski , Anthony Robins

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\citet{zou2021benign} provides…

Machine Learning · Computer Science 2025-06-19 Alexandru Meterez , Depen Morwani , Costin-Andrei Oncescu , Jingfeng Wu , Cengiz Pehlevan , Sham Kakade

We study generalised linear regression and classification for a synthetically generated dataset encompassing different problems of interest, such as learning with random features, neural networks in the lazy training regime, and the hidden…

Statistics Theory · Mathematics 2022-03-28 Federica Gerace , Bruno Loureiro , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Large language models (LLMs) suffer from forgetting of upstream knowledge when fine-tuned. Despite efforts on mitigating forgetting, few have investigated how forgotten upstream examples are dependent on newly learned tasks. Insights on…

Machine Learning · Computer Science 2025-12-09 Xisen Jin , Xiang Ren

Using recent works of one of the authors (VSB) on collapse in generative models and two time scale dynamics in stochastic gradient descent in high dimensions, we give a system theoretic explanation of the memorization phenomenon in…

Machine Learning · Computer Science 2026-05-20 Siva Athreya , Chiranjib Bhattacharya , Vivek S. Borkar