English
Related papers

Related papers: SketchOGD: Memory-Efficient Continual Learning

200 papers

We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the gradient from random linear measurements (sketches) of the…

Optimization and Control · Mathematics 2018-10-19 Filip Hanzely , Konstantin Mishchenko , Peter Richtarik

Sketched gradient algorithms have been recently introduced for efficiently solving the large-scale constrained Least-squares regressions. In this paper we provide novel convergence analysis for the basic method {\it Gradient Projection…

Optimization and Control · Mathematics 2017-06-05 Junqi Tang , Mohammad Golbabaee , Mike Davies

Motivated by the study of matrix elimination orderings in combinatorial scientific computing, we utilize graph sketching and local sampling to give a data structure that provides access to approximate fill degrees of a matrix undergoing…

Data Structures and Algorithms · Computer Science 2023-04-11 Matthew Fahrbach , Gary L. Miller , Richard Peng , Saurabh Sawlani , Junxing Wang , Shen Chen Xu

A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. This unequal importance…

Machine Learning · Computer Science 2022-03-21 Jaehong Yoon , Divyam Madaan , Eunho Yang , Sung Ju Hwang

Sketching and stochastic gradient methods are arguably the most common techniques to derive efficient large scale learning algorithms. In this paper, we investigate their application in the context of nonparametric statistical learning.…

Machine Learning · Statistics 2019-01-25 Luigi Carratino , Alessandro Rudi , Lorenzo Rosasco

Stochastic gradient descent (SGD) is a powerful optimization technique that is particularly useful in online learning scenarios. Its convergence analysis is relatively well understood under the assumption that the data samples are…

Machine Learning · Computer Science 2024-10-03 Ethan Che , Jing Dong , Xin T. Tong

In this report we consider the following problem: Given a trained model that is partially faulty, can we correct its behaviour without having to train the model from scratch? In other words, can we ``debug" neural networks similar to how we…

Machine Learning · Computer Science 2022-06-20 Narsimha Chilkuri , Chris Eliasmith

We propose an online learning algorithm for a class of machine learning models under a separable stochastic approximation framework. The essence of our idea lies in the observation that certain parameters in the models are easier to…

Machine Learning · Computer Science 2023-05-23 Min Gan , Xiang-xiang Su , Guang-yong Chen , Jing Chen

Recent studies on catastrophic forgetting during sequential learning typically focus on fixing the accuracy of the predictions for a previously learned task. In this paper we argue that the outputs of neural networks are subject to rapid…

Machine Learning · Computer Science 2020-02-14 Yuwen Xiong , Mengye Ren , Raquel Urtasun

Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate…

Computer Vision and Pattern Recognition · Computer Science 2024-01-29 Tao He , Tongtong Wu , Dongyang Zhang , Guiduo Duan , Ke Qin , Yuan-Fang Li

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

Reflecting the greater significance of recent history over the distant past in non-stationary environments, $\lambda$-discounted regret has been introduced in online convex optimization (OCO) to gracefully forget past data as new…

Machine Learning · Computer Science 2025-05-27 Wenhao Yang , Sifan Yang , Lijun Zhang

We consider feature selection for applications in machine learning where the dimensionality of the data is so large that it exceeds the working memory of the (local) computing machine. Unfortunately, current large-scale sketching algorithms…

Machine Learning · Computer Science 2021-05-27 Amirali Aghazadeh , Vipul Gupta , Alex DeWeese , O. Ozan Koyluoglu , Kannan Ramchandran

In reinforcement learning (RL), offline learning decoupled learning from data collection and is useful in dealing with exploration-exploitation tradeoff and enables data reuse in many applications. In this work, we study two offline…

Machine Learning · Computer Science 2022-02-08 Jing Dong , Xin T. Tong

Lifelong learning is challenging for deep neural networks due to their susceptibility to catastrophic forgetting. Catastrophic forgetting occurs when a trained network is not able to maintain its ability to accomplish previously learned…

Computer Vision and Pattern Recognition · Computer Science 2019-08-23 Mengyao Zhai , Lei Chen , Fred Tung , Jiawei He , Megha Nawhal , Greg Mori

Many crucial tasks of image processing and computer vision are formulated as inverse problems. Thus, it is of great importance to design fast and robust algorithms to solve these problems. In this paper, we focus on generalized projected…

Image and Video Processing · Electrical Eng. & Systems 2025-12-09 Ali Joundi , Yann Traonmilin , Alasdair Newson

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness,…

Machine Learning · Computer Science 2016-02-29 Thomas Hofmann , Aurelien Lucchi , Simon Lacoste-Julien , Brian McWilliams

As a fundamental issue in lifelong learning, catastrophic forgetting is directly caused by inaccessible historical data; accordingly, if the data (information) were memorized perfectly, no forgetting should be expected. Motivated by that,…

Computer Vision and Pattern Recognition · Computer Science 2020-11-13 Yulai Cong , Miaoyun Zhao , Jianqiao Li , Sijia Wang , Lawrence Carin

This paper introduces a projected functional gradient descent algorithm (P-FGD) for training nonparametric additive quantile regression models in online settings. This algorithm extends the functional stochastic gradient descent framework…

Machine Learning · Statistics 2026-04-13 Haoran Zhan

In recent years, neural networks have demonstrated an outstanding ability to achieve complex learning tasks across various domains. However, they suffer from the "catastrophic forgetting" problem when they face a sequence of learning tasks,…

Machine Learning · Computer Science 2020-04-27 Seyed-Iman Mirzadeh , Mehrdad Farajtabar , Hassan Ghasemzadeh
‹ Prev 1 8 9 10 Next ›