English
Related papers

Related papers: Does the Adam Optimizer Exacerbate Catastrophic Fo…

200 papers

Continual learning, an important aspect of artificial intelligence and machine learning research, focuses on developing models that learn and adapt to new tasks while retaining previously acquired knowledge. Existing continual learning…

Machine Learning · Computer Science 2024-04-04 Liwei Kang , Wee Sun Lee

Neural network optimization remains one of the most consequential yet poorly understood challenges in modern AI research, where improvements in training algorithms can lead to enhanced feature learning in foundation models,…

Machine Learning · Computer Science 2025-12-23 Ansh Nagwekar

Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting…

Machine Learning · Computer Science 2018-05-29 Nitin Kamra , Umang Gupta , Yan Liu

Catastrophic forgetting is a significant challenge in continual learning, in which a model loses prior knowledge when it is fine-tuned on new tasks. This problem is particularly critical for large language models (LLMs) undergoing continual…

Computation and Language · Computer Science 2025-09-03 Ege Süalp , Mina Rezaei

Selective forgetting or removing information from deep neural networks (DNNs) is essential for continual learning and is challenging in controlling the DNNs. Such forgetting is crucial also in a practical sense since the deployed DNNs may…

Machine Learning · Statistics 2021-01-01 Tomohiro Hayase , Suguru Yasutomi , Takashi Katoh

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not…

Machine Learning · Computer Science 2020-03-18 Sina Ghiassian , Banafsheh Rafiee , Yat Long Lo , Adam White

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the…

Machine Learning · Computer Science 2024-07-31 Weichen Lin , Jiaxiang Chen , Ruomin Huang , Hu Ding

Stochastic gradient descent (SGD) optimization methods such as the plain vanilla SGD method and the popular Adam optimizer are nowadays the method of choice in the training of artificial neural networks (ANNs). Despite the remarkable…

Optimization and Control · Mathematics 2024-02-09 Arnulf Jentzen , Adrian Riekert

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

Artificial neural networks (ANNs) show limited performance with scarce or imbalanced training data and face challenges with continuous learning, such as forgetting previously learned data after new tasks training. In contrast, the human…

Machine Learning · Computer Science 2024-10-22 Anthony Bazhenov , Pahan Dewasurendra , Giri P. Krishnan , Jean Erik Delanois

A large obstacle to deploying deep learning models in practice is the process of updating models post-deployment (ideally, frequently). Deep neural networks can cost many thousands of dollars to train. When new data comes in the pipeline,…

Machine Learning · Computer Science 2023-06-21 Rich Harang , Hillary Sanders

First-order optimization algorithms have been proven prominent in deep learning. In particular, algorithms such as RMSProp and Adam are extremely popular. However, recent works have pointed out the lack of ``long-term memory" in Adam-like…

Machine Learning · Computer Science 2020-12-01 Haiwen Huang , Chang Wang , Bin Dong

Deep Neural Networks (DNNs) have two key deficiencies, their dependence on high precision computing and their inability to perform sequential learning, that is, when a DNN is trained on a first task and the same DNN is trained on the next…

Neural and Evolutionary Computing · Computer Science 2020-07-14 Ruthvik Vaila , John Chiasson , Vishal Saxena

Several deep neural ranking models have been proposed in the recent IR literature. While their transferability to one target domain held by a dataset has been widely addressed using traditional domain adaptation strategies, the question of…

Information Retrieval · Computer Science 2021-01-19 Jesus Lovon-Melgarejo , Laure Soulier , Karen Pinel-Sauvagnat , Lynda Tamine

Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated. In this work, we demonstrate that dynamically grown networks outperform…

Neural and Evolutionary Computing · Computer Science 2018-12-03 German I. Parisi , Xu Ji , Stefan Wermter

In this paper, we propose a new method to overcome catastrophic forgetting by adding generative regularization to Bayesian inference framework. Bayesian method provides a general framework for continual learning. We could further construct…

Machine Learning · Computer Science 2021-06-22 Patrick H. Chen , Wei Wei , Cho-jui Hsieh , Bo Dai

Neural language models deployed in real-world applications must continually adapt to new tasks and domains without forgetting previously acquired knowledge. This work presents a comparative empirical study of catastrophic forgetting…

Computation and Language · Computer Science 2026-03-20 Aram Abrahamyan , Sachin Kumar

We introduce Gravity, another algorithm for gradient-based optimization. In this paper, we explain how our novel idea change parameters to reduce the deep learning model's loss. It has three intuitive hyper-parameters that the best values…

Machine Learning · Computer Science 2021-01-25 Dariush Bahrami , Sadegh Pouriyan Zadeh

Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large…

Computer Vision and Pattern Recognition · Computer Science 2019-10-29 Kibok Lee , Kimin Lee , Jinwoo Shin , Honglak Lee

A long-term goal of AI is to produce agents that can learn a diversity of skills throughout their lifetimes and continuously improve those skills via experience. A longstanding obstacle towards that goal is catastrophic forgetting, which is…

Neural and Evolutionary Computing · Computer Science 2018-02-07 Roby Velez , Jeff Clune