English
Related papers

Related papers: Implicit Regularization in Perturbed Deep Matrix F…

200 papers

This paper studies inference in linear models with a high-dimensional parameter matrix that can be well-approximated by a ``spiked low-rank matrix.'' A spiked low-rank matrix has rank that grows slowly compared to its dimensions and nonzero…

Statistics Theory · Mathematics 2023-01-04 Victor Chernozhukov , Christian Hansen , Yuan Liao , Yinchu Zhu

Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" behavior has been observed: the variability of features…

Machine Learning · Computer Science 2023-05-30 Tom Tirer , Haoxiang Huang , Jonathan Niles-Weed

We consider the densest submatrix problem, which seeks the submatrix of fixed size of a given binary matrix that contains the most nonzero entries. This problem is a natural generalization of fundamental problems in combinatorial…

Optimization and Control · Mathematics 2026-03-13 Valentine Olanubi , Phineas Agar , Brendan Ames

We propose a unified framework to solve general low-rank plus sparse matrix recovery problems based on matrix factorization, which covers a broad family of objective functions satisfying the restricted strong convexity and smoothness…

Machine Learning · Statistics 2018-02-21 Xiao Zhang , Lingxiao Wang , Quanquan Gu

In this paper we study the problem of recovering a low-rank matrix from a number of random linear measurements that are corrupted by outliers taking arbitrary values. We consider a nonsmooth nonconvex formulation of the problem, in which we…

Information Theory · Computer Science 2019-07-16 Xiao Li , Zhihui Zhu , Anthony Man-Cho So , Rene Vidal

To understand the empirical success of approximate MAP inference, recent work (Lang et al., 2018) has shown that some popular approximation algorithms perform very well when the input instance is stable. The simplest stability condition…

Machine Learning · Statistics 2020-11-16 Hunter Lang , David Sontag , Aravindan Vijayaraghavan

We identify an implicit under-parameterization phenomenon in value-based deep RL methods that use bootstrapping: when value functions, approximated using deep neural networks, are trained with gradient descent using iterated regression onto…

Machine Learning · Computer Science 2021-10-26 Aviral Kumar , Rishabh Agarwal , Dibya Ghosh , Sergey Levine

In this paper, we study the problem of recovering two unknown signals from their convolution, which is commonly referred to as blind deconvolution. Reformulation of blind deconvolution as a low-rank recovery problem has led to multiple…

Information Theory · Computer Science 2023-03-20 Julia Kostin , Felix Krahmer , Dominik Stöger

Tensor-based methods have recently emerged as a more natural and effective formulation to address many problems in hyperspectral imaging. In hyperspectral unmixing (HU), low-rank constraints on the abundance maps have been shown to act as a…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Tales Imbiriba , Ricardo Augusto Borsoi , José Carlos Moreira Bermudez

Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods often require careful parameter tuning or prior knowledge of the sparsity of the…

Machine Learning · Computer Science 2026-02-02 Lakshmi Jayalal , Sheetal Kalyani

Low-rank modeling has many important applications in computer vision and machine learning. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has demonstrated better empirical…

Machine Learning · Computer Science 2018-07-25 Quanming Yao , James T. Kwok , Taifeng Wang , Tie-Yan Liu

Training deep neural networks in low rank, i.e. with factorised layers, is of particular interest to the community: it offers efficiency over unfactorised training in terms of both memory consumption and training time. Prior work has…

Machine Learning · Computer Science 2022-09-28 Siddhartha Rao Kamalakara , Acyr Locatelli , Bharat Venkitesh , Jimmy Ba , Yarin Gal , Aidan N. Gomez

The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown that when training and sampling are performed perfectly,…

Machine Learning · Statistics 2025-07-08 Tyler Farghly , Patrick Rebeschini , George Deligiannidis , Arnaud Doucet

This paper studies a regularized matrix tri-factorization \(A\approx PDQ\), where \(P\) and \(Q\) are side factors and \(D\) is a central core whose conditioning can be explicitly regularized or constrained. The formulation is a structured…

Numerical Analysis · Mathematics 2026-05-13 Ronald Katende

This paper examines small-signal stability of electrical networks composed dominantly of three-phase grid-following inverters. We show that the mere existence of a high-voltage power flow solution does not necessarily imply small-signal…

Optimization and Control · Mathematics 2020-05-22 Saber Jafarpour , Victor Purba , Sairaj V. Dhople , Brian Johnson , Francesco Bullo

We consider the problem of noisy 1-bit matrix completion under an exact rank constraint on the true underlying matrix $M^*$. Instead of observing a subset of the noisy continuous-valued entries of a matrix $M^*$, we observe a subset of…

Machine Learning · Statistics 2015-02-25 Sonia Bhaskar , Adel Javanmard

Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization --…

Machine Learning · Statistics 2026-05-08 Joseph H. Rudoler , Kevin Tan , Giles Hooker , Konrad P. Kording

Minimum-volume nonnegative matrix factorization (min-vol NMF) has been used successfully in many applications, such as hyperspectral imaging, chemical kinetics, spectroscopy, topic modeling, and audio source separation. However, its…

Machine Learning · Statistics 2025-11-07 Giovanni Barbarino , Nicolas Gillis , Subhayan Saha

Consider a movie recommendation system where apart from the ratings information, side information such as user's age or movie's genre is also available. Unlike standard matrix completion, in this setting one should be able to predict…

Machine Learning · Computer Science 2013-06-05 Prateek Jain , Inderjit S. Dhillon

We develop new perturbation techniques for conducting convergence analysis of various first-order algorithms for a class of nonsmooth optimization problems. We consider the iteration scheme of an algorithm to construct a perturbed…

Optimization and Control · Mathematics 2018-10-25 Xiangfeng Wang , Jane Ye , Xiaoming Yuan , Shangzhi Zeng , Jin Zhang