English
Related papers

Related papers: Fast Updating Truncated SVD for Representation Lea…

200 papers

The rapid development of large-scale deep learning models questions the affordability of hardware platforms, which necessitates the pruning to reduce their computational and memory footprints. Sparse neural networks as the product, have…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Can Jin , Tianjin Huang , Yihua Zhang , Mykola Pechenizkiy , Sijia Liu , Shiwei Liu , Tianlong Chen

Recent work has established an empirically successful framework for adapting learning rates for stochastic gradient descent (SGD). This effectively removes all needs for tuning, while automatically reducing learning rates over time on…

Machine Learning · Computer Science 2013-03-28 Tom Schaul , Yann LeCun

Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e.g., for calculating gradients via…

Machine Learning · Computer Science 2021-11-12 Sami Abu-El-Haija , Hesham Mostafa , Marcel Nassar , Valentino Crespi , Greg Ver Steeg , Aram Galstyan

We introduce and compare new compression approaches to obtain regularized solutions of large linear systems which are commonly encountered in large scale inverse problems. We first describe how to approximate matrix vector operations with a…

Numerical Analysis · Mathematics 2016-08-12 Sergey Voronin , Dylan Mikesell , Guust Nolet

Big data analysis has become a crucial part of new emerging technologies such as the internet of things, cyber-physical analysis, deep learning, anomaly detection, etc. Among many other techniques, dimensionality reduction plays a key role…

Learning a dynamical system from input/output data is a fundamental task in the control design pipeline. In the partially observed setting there are two components to identification: parameter estimation to learn the Markov parameters, and…

Optimization and Control · Mathematics 2021-09-08 Han Wang , James Anderson

As deep learning (DL) techniques become integral to various applications, ensuring model fairness while maintaining high performance has become increasingly critical, particularly in sensitive fields such as medical diagnosis. Although a…

Machine Learning · Computer Science 2025-11-21 Yuanbo Guo , Jun Xia , Yiyu Shi

The power of randomized algorithms in numerical methods have led to fast solutions which use the Singular Value Decomposition (SVD) as a core routine. However, given the large data size of modern and the modest runtime of SVD, most…

Machine Learning · Computer Science 2018-12-20 Hui Han Chin , Paul Pu Liang

A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Wei Dong , Yuan Sun , Yiting Yang , Xing Zhang , Zhijun Lin , Qingsen Yan , Haokui Zhang , Peng Wang , Yang Yang , Hengtao Shen

In order to compute fast approximations to the singular value decompositions (SVD) of very large matrices, randomized sketching algorithms have become a leading approach. However, a key practical difficulty of sketching an SVD is that the…

Machine Learning · Statistics 2020-03-12 Miles E. Lopes , N. Benjamin Erichson , Michael W. Mahoney

Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD-based compression reduces storage and can speed up inference via low-rank factors, yet…

Machine Learning · Computer Science 2026-02-04 Ali Abbasi , Chayne Thrash , Haoran Qin , Shansita Sharma , Sepehr Seifi , Soheil Kolouri

While pruning methods effectively maintain model performance without extra training costs, they often focus solely on preserving crucial connections, overlooking the impact of pruned weights on subsequent fine-tuning or distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Hyeonjin Kim , Jaejun Yoo

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive…

Machine Learning · Statistics 2018-10-02 Qi Deng , Yi Cheng , Guanghui Lan

This article presents two novel adaptive-sparse polynomial dimensional decomposition (PDD) methods for solving high-dimensional uncertainty quantification problems in computational science and engineering. The methods entail global…

Numerical Analysis · Mathematics 2015-06-18 Vaibhav Yadav , Sharif Rahman

We consider $N$-way data arrays and low-rank tensor factorizations where the time mode is coded as a sparse linear combination of temporal elements from an over-complete library. Our method, Shape Constrained Tensor Decomposition (SCTD) is…

Machine Learning · Statistics 2016-08-17 Bethany Lusch , Eric C. Chi , J. Nathan Kutz

Singular value decomposition (SVD) is a standard matrix factorization technique that produces optimal low-rank approximations of matrices. It has diverse applications, including machine learning, data science and signal processing. However,…

Mathematical Software · Computer Science 2019-07-16 Vadim Demchik , Miroslav Bačák , Stefan Bordag

Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. While super-resolution is widely used in…

Graphics · Computer Science 2026-02-10 Martin Bálint , Corentin Salaün , Hans-Peter Seidel , Karol Myszkowski

From linear classifiers to neural networks, image classification has been a widely explored topic in mathematics, and many algorithms have proven to be effective classifiers. However, the most accurate classifiers typically have…

Machine Learning · Statistics 2017-06-30 Elizabeth Newman , Misha Kilmer , Lior Horesh

Sparsity regularized loss minimization problems play an important role in various fields including machine learning, data mining, and modern statistics. Proximal gradient descent method and coordinate descent method are the most popular…

Machine Learning · Computer Science 2023-11-13 Runxue Bao , Bin Gu , Heng Huang

Temporal difference (TD) methods constitute a class of methods for learning predictions in multi-step prediction problems, parameterized by a recency factor lambda. Currently the most important application of these methods is to temporal…

Artificial Intelligence · Computer Science 2008-02-03 P. Cichosz