English
Related papers

Related papers: Accuracy of empirical projections of high-dimensio…

200 papers

We consider a general model for high-dimensional empirical risk minimization whereby the data $\mathbf{x}_i$ are $d$-dimensional Gaussian vectors, the model is parametrized by $\mathbf{\Theta}\in\mathbb{R}^{d\times k}$, and the loss depends…

Machine Learning · Statistics 2026-01-26 Kiana Asgari , Andrea Montanari , Basil Saeed

Randomized algorithms have proven to perform well on a large class of numerical linear algebra problems. Their theoretical analysis is critical to provide guarantees on their behaviour, and in this sense, the stochastic analysis of the…

Numerical Analysis · Mathematics 2025-10-01 Alexandre Scotto Di Perrotolo , Youssef Diouane , Selime Gürol , Xavier Vasseur

We consider the problem of robustifying high-dimensional structured estimation. Robust techniques are key in real-world applications which often involve outliers and data corruption. We focus on trimmed versions of structurally regularized…

Machine Learning · Statistics 2017-08-22 Eunho Yang , Aurelie Lozano , Aleksandr Aravkin

Estimation and prediction problems for dense signals are often framed in terms of minimax problems over highly symmetric parameter spaces. In this paper, we study minimax problems over l2-balls for high-dimensional linear models with…

Statistics Theory · Mathematics 2012-03-22 Lee Dicker

A general theory for Gaussian mean estimation that automatically adapts to unknown sparsity under arbitrary norms is proposed. The theory is applied to produce adaptively minimax rate-optimal estimators in high dimensional regression and…

Statistics Theory · Mathematics 2015-12-01 Sourav Chatterjee

In this paper, we study random subsampling of Gaussian process regression, one of the simplest approximation baselines, from a theoretical perspective. Although subsampling discards a large part of training data, we show provable guarantees…

Machine Learning · Statistics 2019-01-29 Kohei Hayashi , Masaaki Imaizumi , Yuichi Yoshida

We describe an elementary method to get non-asymptotic estimates for the moments of Hermitian random matrices whose elements are Gaussian independent random variables. As the basic example, we consider the GUE matrices. Immediate…

Mathematical Physics · Physics 2007-05-23 O. Khorunzhiy

Gaussian processes (GP) are Bayesian non-parametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size.…

Machine Learning · Computer Science 2014-08-12 Jie Chen , Nannan Cao , Kian Hsiang Low , Ruofei Ouyang , Colin Keng-Yan Tan , Patrick Jaillet

Gaussian processes (GP) are Bayesian non-parametric models that are widely used for probabilistic regression. Unfortunately, it cannot scale well with large data nor perform real-time predictions due to its cubic time cost in the data size.…

Machine Learning · Statistics 2013-05-27 Jie Chen , Nannan Cao , Kian Hsiang Low , Ruofei Ouyang , Colin Keng-Yan Tan , Patrick Jaillet

We consider the bound-constrained global optimization of functions with low effective dimensionality, that are constant along an (unknown) linear subspace and only vary over the effective (complement) subspace. We aim to implicitly explore…

Optimization and Control · Mathematics 2020-09-23 Coralia Cartis , Estelle Massart , Adilet Otemissov

We present randomized algorithms for estimating the trace and deter- minant of Hermitian positive semi-definite matrices. The algorithms are based on subspace iteration, and access the matrix only through matrix vector products. We analyse…

Numerical Analysis · Mathematics 2017-02-17 Arvind K. Saibaba , Alen Alexanderian , Ilse C. F. Ipsen

This article provides a new toolbox to derive sparse recovery guarantees from small deviations on extreme singular values or extreme eigenvalues obtained in Random Matrix Theory. This work is based on Restricted Isometry Constants (RICs)…

Statistics Theory · Mathematics 2018-11-15 Sandrine Dallaporta , Yohann De Castro

Low-rank matrix completion consists of computing a matrix of minimal complexity that recovers a given set of observations as accurately as possible. Unfortunately, existing methods for matrix completion are heuristics that, while highly…

Machine Learning · Computer Science 2026-03-12 Dimitris Bertsimas , Ryan Cory-Wright , Sean Lo , Jean Pauphilet

Motivated by the Central Limit Theorem, in this paper, we study both universal and non-universal simulations of random variables with an arbitrary target distribution $Q_{Y}$ by general mappings, not limited to linear ones (as in the…

Probability · Mathematics 2018-12-05 Lei Yu

We present an analysis of sets of matrices with rank less than or equal to a specified number $s$. We provide a simple formula for the normal cone to such sets, and use this to show that these sets are prox-regular at all points with rank…

Optimization and Control · Mathematics 2018-09-24 D. Russell Luke

We study convex empirical risk minimization for high-dimensional inference in binary models. Our first result sharply predicts the statistical performance of such estimators in the linear asymptotic regime under isotropic Gaussian features.…

Statistics Theory · Mathematics 2020-02-27 Hossein Taheri , Ramtin Pedarsani , Christos Thrampoulidis

We study the performance of a wide class of convex optimization-based estimators for recovering a signal from corrupted one-bit measurements in high-dimensions. Our general result predicts sharply the performance of such estimators in the…

Statistics Theory · Mathematics 2020-01-27 Hossein Taheri , Ramtin Pedarsani , Christos Thrampoulidis

We propose a unified framework for estimating low-rank matrices through nonconvex optimization based on gradient descent algorithm. Our framework is quite general and can be applied to both noisy and noiseless observations. In the general…

Machine Learning · Statistics 2016-10-18 Lingxiao Wang , Xiao Zhang , Quanquan Gu

The smallest singular value and condition number play important roles in numerical linear algebra and the analysis of algorithms. In numerical analysis with randomness, many previous works make Gaussian assumptions, which are not general…

Probability · Mathematics 2022-11-09 Haoyu Wang

Existing results for low-rank matrix recovery largely focus on quadratic loss, which enjoys favorable properties such as restricted strong convexity/smoothness (RSC/RSM) and well conditioning over all low rank matrices. However, many…

Machine Learning · Statistics 2021-11-17 Lijun Ding , Yuqian Zhang , Yudong Chen