English
Related papers

Related papers: Generalized High-Dimensional Trace Regression via …

200 papers

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Yang Zhong , Atsuto Maki

In this paper we consider the trace regression model. Assume that we observe a small set of entries or linear combinations of entries of an unknown matrix $A_0$ corrupted by noise. We propose a new rank penalized estimator of $A_0$. For…

Statistics Theory · Mathematics 2011-09-14 Olga Klopp

Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem.…

Machine Learning · Computer Science 2017-08-01 Carlo Ciliberto , Dimitris Stamos , Massimiliano Pontil

High-dimensional matrix regression has been studied in various aspects, such as statistical properties, computational efficiency and application to specific instances including multivariate regression, system identification and matrix…

Statistics Theory · Mathematics 2024-03-06 Xin Li , Dongya Wu

It is by now well-established that modern over-parameterized models seem to elude the bias-variance tradeoff and generalize well despite overfitting noise. Many recent works attempt to analyze this phenomenon in the relatively tractable…

Machine Learning · Computer Science 2024-02-21 Daniel Barzilai , Ohad Shamir

Low-rank modeling has a lot of important applications in machine learning, computer vision and social network analysis. While the matrix rank is often approximated by the convex nuclear norm, the use of nonconvex low-rank regularizers has…

Numerical Analysis · Computer Science 2016-05-02 Quanming Yao , James T. Kwok , Wenliang Zhong

The problem of finding the maximum likelihood estimates for the regression coefficients in generalised linear models with an L1 sparsity penalty is shown to be equivalent to minimising the unpenalised maximum log-likelihood function over a…

Methodology · Statistics 2015-12-21 Tom Michoel

Nonconvex regularization has been popularly used in low-rank matrix learning. However, extending it for low-rank tensor learning is still computationally expensive. To address this problem, we develop an efficient solver for use with a…

Machine Learning · Computer Science 2022-05-09 Quanming Yao , Yaqing Wang , Bo Han , James Kwok

In this paper we present a general convex optimization approach for solving high-dimensional multiple response tensor regression problems under low-dimensional structural assumptions. We consider using convex and weakly decomposable…

Statistics Theory · Mathematics 2017-04-17 Garvesh Raskutti , Ming Yuan , Han Chen

We consider the problem of recovering a lowrank matrix M from a small number of random linear measurements. A popular and useful example of this problem is matrix completion, in which the measurements reveal the values of a subset of the…

Information Theory · Computer Science 2009-10-05 Emmanuel J. Candes , Yaniv Plan

Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

We propose new methods for multivariate linear regression when the regression coefficient matrix is sparse and the error covariance matrix is dense. We assume that the error covariance matrix has equicorrelation across the response…

Methodology · Statistics 2025-08-13 Daeyoung Ham , Bradley S. Price , Adam J. Rothman

Motivated by the learned iterative soft thresholding algorithm (LISTA), we introduce a general class of neural networks suitable for sparse reconstruction from few linear measurements. By allowing a wide range of degrees of weight-sharing…

Machine Learning · Computer Science 2022-01-19 Ekkehard Schnoor , Arash Behboodi , Holger Rauhut

Originally developed for imputing missing entries in low rank, or approximately low rank matrices, matrix completion has proven widely effective in many problems where there is no reason to assume low-dimensional linear structure in the…

Statistics Theory · Mathematics 2021-05-06 Yunhua Xiang , Tianyu Zhang , Xu Wang , Ali Shojaie , Noah Simon

Sparse models for high-dimensional linear regression and machine learning have received substantial attention over the past two decades. Model selection, or determining which features or covariates are the best explanatory variables, is…

Machine Learning · Statistics 2019-10-15 Yuan Li , Benjamin Mark , Garvesh Raskutti , Rebecca Willett , Hyebin Song , David Neiman

We propose a loop optimization algorithm based on nuclear norm regularization for tensor network. The key ingredient of this scheme is to introduce a rank penalty term proposed in the context of data processing. Compared to standard…

Statistical Mechanics · Physics 2024-11-07 Kenji Homma , Tsuyoshi Okubo , Naoki Kawashima

This paper provides a comprehensive estimation framework via nuclear norm plus $l_1$ norm penalization for high-dimensional approximate factor models with a sparse residual covariance. The underlying assumptions allow for non-pervasive…

Statistics Theory · Mathematics 2021-04-07 Matteo Farnè , Angela Montanari

We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR).…

Machine Learning · Computer Science 2018-02-07 Markus Kliegl , Siddharth Goyal , Kexin Zhao , Kavya Srinet , Mohammad Shoeybi

Meta-learning involves training models on a variety of training tasks in a way that enables them to generalize well on new, unseen test tasks. In this work, we consider meta-learning within the framework of high-dimensional multivariate…

Statistics Theory · Mathematics 2024-04-01 Yanhao Jin , Krishnakumar Balasubramanian , Debashis Paul

In high-dimensional regression, we attempt to estimate a parameter vector $\beta_0\in\mathbb{R}^p$ from $n\lesssim p$ observations $\{(y_i,x_i)\}_{i\leq n}$ where $x_i\in\mathbb{R}^p$ is a vector of predictors and $y_i$ is a response…

Statistics Theory · Mathematics 2022-02-08 Michael Celentano , Andrea Montanari