English
Related papers

Related papers: Lifelong Learning with Sketched Structural Regular…

200 papers

When machine learning models are trained continually on a sequence of tasks, they are often liable to forget what they learned on previous tasks--a phenomenon known as catastrophic forgetting. Proposed solutions to catastrophic forgetting…

Machine Learning · Computer Science 2025-12-18 Youngjae Min , Benjamin Wright , Jeremy Bernstein , Navid Azizan

The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Sayna Ebrahimi , Suzanne Petryk , Akash Gokul , William Gan , Joseph E. Gonzalez , Marcus Rohrbach , Trevor Darrell

In reinforcement learning (RL), Q-learning is a fundamental algorithm whose convergence is guaranteed in the tabular setting. However, this convergence guarantee does not hold under linear function approximation. To overcome this…

Machine Learning · Computer Science 2026-02-04 Hyukjun Yang , Han-Dong Lim , Donghwan Lee

Catastrophic forgetting is the primary challenge that hinders continual learning, which refers to a neural network ability to sequentially learn multiple tasks while retaining previously acquired knowledge. Elastic Weight Consolidation, a…

Machine Learning · Computer Science 2025-07-15 Brandon Shuen Yi Loke , Filippo Quadri , Gabriel Vivanco , Maximilian Casagrande , Saúl Fenollosa

This paper describes a suite of algorithms for constructing low-rank approximations of an input matrix from a random linear image of the matrix, called a sketch. These methods can preserve structural properties of the input matrix, such as…

Numerical Analysis · Computer Science 2018-01-03 Joel A. Tropp , Alp Yurtsever , Madeleine Udell , Volkan Cevher

Continual learning aims to emulate the human ability to continually accumulate knowledge over sequential tasks. The main challenge is to maintain performance on previously learned tasks after learning new tasks, i.e., to avoid catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Yunhao Ge , Yuecheng Li , Shuo Ni , Jiaping Zhao , Ming-Hsuan Yang , Laurent Itti

In recent years, randomized methods for numerical linear algebra have received growing interest as a general approach to large-scale problems. Typically, the essential ingredient of these methods is some form of randomized dimension…

Machine Learning · Statistics 2019-04-05 Miles E. Lopes , Shusen Wang , Michael W. Mahoney

For linear systems $Ax=b$ we develop iterative algorithms based on a sketch-and-project approach. By using judicious choices for the sketch, such as the history of residuals, we develop weighting strategies that enable short recursive…

Numerical Analysis · Mathematics 2024-07-02 Johannes J Brust , Michael A Saunders

Probabilistic ideas and tools have recently begun to permeate into several fields where they had traditionally not played a major role, including fields such as numerical linear algebra and optimization. One of the key ways in which these…

Numerical Analysis · Mathematics 2016-12-20 Robert M. Gower

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Computation and Language · Computer Science 2025-02-18 Shezheng Song , Hao Xu , Jun Ma , Shasha Li , Long Peng , Qian Wan , Xiaodong Liu , Jie Yu

Continual learning algorithms which keep the parameters of new tasks close to that of previous tasks, are popular in preventing catastrophic forgetting in sequential task learning settings. However, 1) the performance for the new continual…

Machine Learning · Computer Science 2023-07-21 Wei Cong , Yang Cong , Gan Sun , Yuyang Liu , Jiahua Dong

Regularization plays a major role in modern deep learning. From classic techniques such as L1,L2 penalties to other noise-based methods such as Dropout, regularization often yields better generalization properties by avoiding overfitting.…

Machine Learning · Statistics 2021-06-08 Soufiane Hayou , Fadhel Ayed

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks),…

Machine Learning · Statistics 2021-08-06 Jary Pomponi , Simone Scardapane , Aurelio Uncini

We study the common continual learning setup where an overparameterized model is sequentially fitted to a set of jointly realizable tasks. We analyze forgetting, defined as the loss on previously seen tasks, after $k$ iterations. For…

Machine Learning · Computer Science 2026-01-05 Itay Evron , Ran Levinstein , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Nathan Srebro

Array synthetic aperture radar (Array-SAR), also known as tomographic SAR (TomoSAR), has demonstrated significant potential for high-quality 3D mapping, particularly in urban areas.While deep learning (DL) methods have recently shown…

Image and Video Processing · Electrical Eng. & Systems 2024-12-24 Yu Ren , Xu Zhan , Yunqiao Hu , Xiangdong Ma , Liang Liu , Mou Wang , Jun Shi , Shunjun Wei , Tianjiao Zeng , Xiaoling Zhang

Catastrophic forgetting undermines the effectiveness of deep neural networks (DNNs) in scenarios such as continual learning and lifelong learning. While several methods have been proposed to tackle this problem, there is limited work…

Machine Learning · Computer Science 2022-08-16 Ekdeep Singh Lubana , Puja Trivedi , Danai Koutra , Robert P. Dick

In planning and reinforcement learning, the identification of common subgoal structures across problems is important when goals are to be achieved over long horizons. Recently, it has been shown that such structures can be expressed as…

Artificial Intelligence · Computer Science 2025-08-18 Michael Aichmüller , Hector Geffner

With the rise of deep reinforcement learning (RL) methods, many complex robotic manipulation tasks are being solved. However, harnessing the full power of deep learning requires large datasets. Online-RL does not suit itself readily into…

Robotics · Computer Science 2024-11-20 Sudhir Pratap Yadav , Rajendra Nagar , Suril V. Shah

Plasticity Loss is an increasingly important phenomenon that refers to the empirical observation that as a neural network is continually trained on a sequence of changing tasks, its ability to adapt to a new task diminishes over time. We…

Machine Learning · Computer Science 2025-09-30 Vivek F. Farias , Adam D. Jozefiak

The frequent directions (FD) technique is a deterministic approach for online sketching that has many applications in machine learning. The conventional FD is a heuristic procedure that often outputs rank deficient matrices. To overcome the…

Machine Learning · Computer Science 2019-02-26 Luo Luo , Cheng Chen , Zhihua Zhang , Wu-Jun Li , Tong Zhang