English
Related papers

Related papers: Extreme value theory for singular subspace estimat…

200 papers

Extreme value theory is part and parcel of any study of order statistics in one dimension. Our aim here is to consider such large sample theory for the maximum distance to the origin, and the related maximum "interpoint distance," in…

Probability · Mathematics 2015-10-30 Sreenivasa Rao Jammalamadaka , Svante Janson

The Gaussian kernel and its traditional normalizations (e.g., row-stochastic) are popular approaches for assessing similarities between data points. Yet, they can be inaccurate under high-dimensional noise, especially if the noise magnitude…

Statistics Theory · Mathematics 2023-07-12 Boris Landa , Xiuyuan Cheng

Factorization of matrices where the rank of the two factors diverges linearly with their sizes has many applications in diverse areas such as unsupervised representation learning, dictionary learning or sparse coding. We consider a setting…

Disordered Systems and Neural Networks · Physics 2022-08-11 Antoine Maillard , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Random label noises (or observational noises) widely exist in practical machine learning settings. While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the…

Machine Learning · Computer Science 2023-04-04 Haoyi Xiong , Xuhong Li , Boyang Yu , Zhanxing Zhu , Dongrui Wu , Dejing Dou

This study evaluates thresholds for removing singular values from singular value decomposition-based low-rank approximations of deep neural network weight matrices. Each weight matrix is modeled as the sum of signal and noise matrices. The…

Machine Learning · Statistics 2026-04-10 Kohei Nishikawa , Koki Shimizu , Hiroki Hashiguchi

This paper considers the problem of estimating a low-rank matrix from the observation of all or a subset of its entries in the presence of Poisson noise. When we observe all entries, this is a problem of matrix denoising; when we observe…

Machine Learning · Statistics 2024-04-22 Andrew D. McRae , Mark A. Davenport

In many real-world classification problems, the labels of training examples are randomly corrupted. Most previous theoretical work on classification with label noise assumes that the two classes are separable, that the label noise is…

Machine Learning · Statistics 2016-08-08 Gilles Blanchard , Marek Flaska , Gregory Handy , Sara Pozzi , Clayton Scott

In this paper we study the problem of signal detection in Gaussian noise in a distributed setting where the local machines in the star topology can communicate a single bit of information. We derive a lower bound on the Euclidian norm that…

Information Theory · Computer Science 2022-02-28 Botond Szabo , Lasse Vuursteen , Harry van Zanten

We consider recovery of low-rank matrices from noisy data by shrinkage of singular values, in which a single, univariate nonlinearity is applied to each of the empirical singular values. We adopt an asymptotic framework, in which the matrix…

Statistics Theory · Mathematics 2016-05-17 Matan Gavish , David L. Donoho

An unknown $m$ by $n$ matrix $X_0$ is to be estimated from noisy measurements $Y=X_0+Z$, where the noise matrix $Z$ has i.i.d. Gaussian entries. A popular matrix denoising scheme solves the nuclear norm penalization problem $\operatorname…

Statistics Theory · Mathematics 2014-11-05 David Donoho , Matan Gavish

We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…

Machine Learning · Statistics 2022-03-17 Diego Granziol , Nicholas Baskerville

The low-complexity assumption in linear systems can often be expressed as rank deficiency in data matrices with generalized Hankel structure. This makes it possible to denoise the data by estimating the underlying structured low-rank…

Systems and Control · Electrical Eng. & Systems 2021-11-10 Mingzhou Yin , Roy S. Smith

Perturbation theory is developed to analyze the impact of noise on data and has been an essential part of numerical analysis. Recently, it has played an important role in designing and analyzing matrix algorithms. One of the most useful…

Probability · Mathematics 2023-11-21 Abhinav Bhardwaj , Van Vu

We study high-dimensional least-squares regression within a subgaussian statistical learning framework with heterogeneous noise. It includes $s$-sparse and $r$-low-rank least-squares regression when a fraction $\epsilon$ of the labels are…

Statistics Theory · Mathematics 2023-11-01 Philip Thompson

A low rank matrix X has been contaminated by uniformly distributed noise, missing values, outliers and corrupt entries. Reconstruction of X from the singular values and singular vectors of the contaminated matrix Y is a key problem in…

Information Theory · Computer Science 2017-11-21 Danny Barash , Matan Gavish

We establish theoretical guarantees for the expected prediction error of the exponential weighting aggregate in the case of multivariate regression that is when the label vector is multidimensional. We consider the regression model with…

Statistics Theory · Mathematics 2018-06-26 Arnak S. Dalalyan

For a fixed symmetric matrix A and symmetric perturbation E we develop purely deterministic bounds on how invariant subspaces of A and A+E can differ when measured by a suitable "row-wise" metric rather than via traditional measures of…

Numerical Analysis · Mathematics 2020-06-22 Anil Damle , Yuekai Sun

Semantic segmentation and change detection are two fundamental challenges in remote sensing, requiring models to capture either spatial semantics or temporal differences from satellite imagery. Existing deep learning models often struggle…

Computer Vision and Pattern Recognition · Computer Science 2026-05-01 Ali Shibli , Andrea Nascetti , Yifang Ban

The stochastic block model is a popular tool for detecting community structures in network data. Detecting the difference between two community structures is an important issue for stochastic block models. However, the two-sample test has…

Methodology · Statistics 2022-12-21 Kang Fu , Jianwei Hu , Seydou Keita , Hao Liu

We study $\textit{sparse singular value certificates}$ for random rectangular matrices. If $M$ is an $n \times d$ matrix with independent Gaussian entries, we give a new family of polynomial-time algorithms which can certify upper bounds on…

Data Structures and Algorithms · Computer Science 2024-12-31 Ilias Diakonikolas , Samuel B. Hopkins , Ankit Pensia , Stefan Tiegel