English
Related papers

Related papers: AlterSGD: Finding Flat Minima for Continual Learni…

200 papers

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

Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters. Trying different combinations can be quite labor-intensive and…

Machine Learning · Computer Science 2017-06-13 Kaifeng Lv , Shunhua Jiang , Jian Li

The learning rate is an important tuning parameter for stochastic gradient descent (SGD) and can greatly influence its performance. However, appropriate selection of a learning rate schedule across all iterations typically requires a…

Machine Learning · Computer Science 2025-05-29 Nikola Surjanovic , Alexandre Bouchard-Côté , Trevor Campbell

The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts…

Machine Learning · Computer Science 2019-07-08 Huaiyu Li , Weiming Dong , Bao-Gang Hu

Making deep neural networks robust to small adversarial noises has recently been sought in many applications. Adversarial training through iterative projected gradient descent (PGD) has been established as one of the mainstream ideas to…

Machine Learning · Computer Science 2021-03-30 Zeinab Golgooni , Mehrdad Saberi , Masih Eskandar , Mohammad Hossein Rohban

In federated distributed learning, the goal is to optimize a global training objective defined over distributed devices, where the data shard at each device is sampled from a possibly different distribution (a.k.a., heterogeneous or non…

Machine Learning · Computer Science 2019-12-10 Farzin Haddadpour , Mehrdad Mahdavi

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

Machine Learning · Computer Science 2019-11-27 David Rolnick , Arun Ahuja , Jonathan Schwarz , Timothy P. Lillicrap , Greg Wayne

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

Machine Learning · Computer Science 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

Stochastic nested optimization, including stochastic compositional, min-max and bilevel optimization, is gaining popularity in many machine learning applications. While the three problems share the nested structure, existing works often…

Machine Learning · Statistics 2021-06-28 Tianyi Chen , Yuejiao Sun , Wotao Yin

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

Flatness of the loss landscape has been widely studied as an important perspective for understanding the behavior and generalization of deep learning algorithms. Motivated by this view, we propose Flatness-Aware Stochastic Gradient Langevin…

Machine Learning · Computer Science 2026-05-28 Stefano Bruno , Youngsik Hwang , Jaehyeon An , Sotirios Sabanis , Dong-Young Lim

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

The vast majority of successful deep neural networks are trained using variants of stochastic gradient descent (SGD) algorithms. Recent attempts to improve SGD can be broadly categorized into two approaches: (1) adaptive learning rate…

Machine Learning · Computer Science 2019-12-04 Michael R. Zhang , James Lucas , Geoffrey Hinton , Jimmy Ba

Pretrained knowledge memorized in LLMs raises critical concerns over safety and privacy, which has motivated LLM Unlearning as a technique for selectively removing the influences of undesirable knowledge. Existing approaches, rooted in…

Computation and Language · Computer Science 2026-02-04 Zhengbang Yang , Yisheng Zhong , Junyuan Hong , Zhuangdi Zhu

Multimodal continual instruction tuning enables multimodal large language models to sequentially adapt to new tasks while building upon previously acquired knowledge. However, this continual learning paradigm faces the significant challenge…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Songze Li , Mingyu Gao , Tonghua Su , Xu-Yao Zhang , Zhongjie Wang

Neural networks trained by empirical risk minimization often suffer from overfitting, especially to specific samples or domains, which leads to poor generalization. Curriculum Learning (CL) addresses this issue by selecting training samples…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Hiroaki Aizawa , Yoshikazu Hayashi

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Yonatan Sverdlov , Shimon Ullman

It is known that the standard stochastic gradient descent (SGD) optimization method, as well as accelerated and adaptive SGD optimization methods such as the Adam optimizer fail to converge if the learning rates do not converge to zero (as,…

Optimization and Control · Mathematics 2024-06-21 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Deep representation learning methods struggle with continual learning, suffering from both catastrophic forgetting of useful units and loss of plasticity, often due to rigid and unuseful units. While many methods address these two issues…

Machine Learning · Computer Science 2024-05-02 Mohamed Elsayed , A. Rupam Mahmood

Modern representation learning methods often struggle to adapt quickly under non-stationarity because they suffer from catastrophic forgetting and decaying plasticity. Such problems prevent learners from fast adaptation since they may…

Machine Learning · Computer Science 2023-04-28 Mohamed Elsayed , A. Rupam Mahmood