English
Related papers

Related papers: Lifelong Learning with Sketched Structural Regular…

200 papers

The power method is one of the most fundamental tools for extracting top principal components from data through low-rank matrix approximation. Yet, when the target rank is large, the cost of matrix multiplication associated with this…

Numerical Analysis · Mathematics 2026-05-12 Shabarish Chenakkod , Michał Dereziński

We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each…

Machine Learning · Computer Science 2024-11-22 Sanchar Palit , Biplab Banerjee , Subhasis Chaudhuri

Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint…

Machine Learning · Computer Science 2018-12-06 Jian Peng , Jiang Hao , Zhuo Li , Enqiang Guo , Xiaohong Wan , Deng Min , Qing Zhu , Haifeng Li

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Computation and Language · Computer Science 2024-09-10 Sonam Gupta , Yatin Nandwani , Asaf Yehudai , Mayank Mishra , Gaurav Pandey , Dinesh Raghu , Sachindra Joshi

We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low-rank approximation and regression. In the learning-based…

Machine Learning · Computer Science 2024-04-12 Yi Li , Honghao Lin , Simin Liu , Ali Vakilian , David P. Woodruff

Matrix sketching is a recently developed data compression technique. An input matrix A is efficiently approximated with a smaller matrix B, so that B preserves most of the properties of A up to some guaranteed approximation ratio. In so…

Machine Learning · Statistics 2019-12-03 Roberta Falcone , Angela Montanari , Laura Anderlucci

In radial basis function neural network (RBFNN) based real-time learning tasks, forgetting mechanisms are widely used such that the neural network can keep its sensitivity to new data. However, with forgetting mechanisms, some useful…

Systems and Control · Electrical Eng. & Systems 2023-08-09 Yiming Fei , Jiangang Li , Yanan Li

As the parameters of Large Language Models (LLMs) have scaled to hundreds of billions, the demand for efficient training methods -- balancing faster computation and reduced memory usage without sacrificing accuracy -- has become more…

Machine Learning · Computer Science 2025-03-03 Kaan Ozkara , Tao Yu , Youngsuk Park

Although quantization has emerged as a promising approach to reducing computational complexity across various high-level vision tasks, it inevitably leads to accuracy loss in image super-resolution (SR) networks. This is due to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Cheeun Hong , Kyoung Mu Lee

Matrix-valued optimization tasks, including those involving symmetric positive definite (SPD) matrices, arise in a wide range of applications in machine learning, data science and statistics. Classically, such problems are solved via…

Optimization and Control · Mathematics 2024-10-15 Andrew Cheng , Melanie Weber

Catastrophic forgetting(CF) is a significant challenge in continual learning (CL). In regularization-based approaches to mitigate CF, modifications to important training parameters are penalized in subsequent tasks using an appropriate loss…

Machine Learning · Computer Science 2023-12-18 Sahil Nokhwal , Nirman Kumar

Extended sequence generation often leads to degradation in contextual consistency due to the inability of conventional self-attention mechanisms to effectively retain long-range dependencies. Existing approaches, including memory…

Computation and Language · Computer Science 2025-01-30 Jonathan Teel , Jocasta Cumberbatch , Raphael Benington , Quentin Baskerville

There is growing body of learning problems for which it is natural to organize the parameters into matrix, so as to appropriately regularize the parameters under some matrix norm (in order to impose some more sophisticated prior knowledge).…

Machine Learning · Computer Science 2010-10-19 Sham M. Kakade , Shai Shalev-Shwartz , Ambuj Tewari

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…

Machine Learning · Computer Science 2021-05-06 Yuyang Gao , Giorgio A. Ascoli , Liang Zhao

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Computation and Language · Computer Science 2026-01-13 Jinyi Han , Zixiang Di , Zishang Jiang , Ying Liao , Jiaqing Liang , Yongqi Wang , Yanghua Xiao

In this work, we study the phenomenon of catastrophic forgetting in the graph representation learning scenario. The primary objective of the analysis is to understand whether classical continual learning techniques for flat and sequential…

Machine Learning · Computer Science 2021-03-23 Antonio Carta , Andrea Cossu , Federico Errica , Davide Bacciu

The phenomenon of implicit regularization has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails that gradient descent dynamics in many neural…

Machine Learning · Computer Science 2024-02-28 Hong T. M. Chu , Subhro Ghosh , Chi Thanh Lam , Soumendu Sundar Mukherjee

In deep neural nets, lower level embedding layers account for a large portion of the total number of parameters. Tikhonov regularization, graph-based regularization, and hard parameter sharing are approaches that introduce explicit biases…

Machine Learning · Computer Science 2020-10-06 Liwei Wu , Shuqing Li , Cho-Jui Hsieh , James Sharpnack

Laplacian regularized stratified models (LRSM) are models that utilize the explicit or implicit network structure of the sub-problems as defined by the categorical features called strata (e.g., age, region, time, forecast horizon, etc.),…

Machine Learning · Statistics 2023-05-05 Ziheng Cheng , Junzi Zhang , Akshay Agrawal , Stephen Boyd

Continual learning in neural networks suffers from a phenomenon called catastrophic forgetting, in which a network quickly forgets what was learned in a previous task. The human brain, however, is able to continually learn new tasks and…

Machine Learning · Computer Science 2022-10-07 Tananun Songdechakraiwut , Xiaoshuang Yin , Barry D. Van Veen
‹ Prev 1 3 4 5 6 7 10 Next ›