English
Related papers

Related papers: Langevin dynamics for high-dimensional optimizatio…

200 papers

We review studies of an evolution operator L for a discrete Langevin equation with a strongly hyperbolic classical dynamics and a Gaussian noise. The leading eigenvalue of L yields a physically measurable property of the dynamical system,…

Chaotic Dynamics · Physics 2022-10-12 Gergely Palla , Gabor Vattay , Andre Voros , Niels Sondergaard , Carl Philip Dettmann

We perform a finite sample analysis of the detection levels for sparse principal components of a high-dimensional covariance matrix. Our minimax optimal test is based on a sparse eigenvalue statistic. Alas, computing this test is known to…

Statistics Theory · Mathematics 2014-01-30 Quentin Berthet , Philippe Rigollet

We study the dynamics of an online algorithm for learning a sparse leading eigenvector from samples generated from a spiked covariance model. This algorithm combines the classical Oja's method for online PCA with an element-wise…

Information Theory · Computer Science 2016-09-09 Chuang Wang , Yue M. Lu

Langevin diffusion is a powerful method for nonconvex optimization, which enables the escape from local minima by injecting noise into the gradient. In particular, the temperature parameter controlling the noise level gives rise to a…

Machine Learning · Statistics 2020-07-07 Yi Chen , Jinglin Chen , Jing Dong , Jian Peng , Zhaoran Wang

Driven by a wide range of applications, many principal subspace estimation problems have been studied individually under different structural constraints. This paper presents a unified framework for the statistical analysis of a general…

Statistics Theory · Mathematics 2020-11-17 T. Tony Cai , Hongzhe Li , Rong Ma

Consider a dataset of vector-valued observations that consists of noisy inliers, which are explained well by a low-dimensional subspace, along with some number of outliers. This work describes a convex optimization problem, called REAPER,…

Information Theory · Computer Science 2015-07-24 Gilad Lerman , Michael McCoy , Joel A. Tropp , Teng Zhang

We study sampling as optimization in the space of measures. We focus on gradient flow-based optimization with the Langevin dynamics as a case study. We investigate the source of the bias of the unadjusted Langevin algorithm (ULA) in…

Optimization and Control · Mathematics 2018-06-08 Andre Wibisono

Optimal symbol detection in multiple-input multiple-output (MIMO) systems is known to be an NP-hard problem. Hence, the objective of any detector of practical relevance is to get reasonably close to the optimal solution while keeping the…

Signal Processing · Electrical Eng. & Systems 2022-02-25 Nicolas Zilberstein , Chris Dick , Rahman Doost-Mohammady , Ashutosh Sabharwal , Santiago Segarra

Point process modeling is gaining increasing attention, as point process type data are emerging in numerous scientific applications. In this article, motivated by a neuronal spike trains study, we propose a novel point process regression…

Methodology · Statistics 2020-12-10 Xiwei Tang , Lexin Li

This paper addresses the problem of sparse phase retrieval, a fundamental inverse problem in applied mathematics, physics, and engineering, where a signal need to be reconstructed using only the magnitude of its transformation while phase…

Machine Learning · Statistics 2025-04-15 The Tien Mai

Unlike the matrix case, computing low-rank approximations of tensors is NP-hard and numerically ill-posed in general. Even the best rank-1 approximation of a tensor is NP-hard. In this paper, we use convex optimization to develop…

Statistics Theory · Mathematics 2016-09-14 Anil Aswani

Hyperparameter tuning is one of the essential steps to guarantee the convergence of machine learning models. We argue that intuition about the optimal choice of hyperparameters for stochastic gradient descent can be obtained by studying a…

Disordered Systems and Neural Networks · Physics 2025-12-12 Chanju Park , Biagio Lucini , Gert Aarts

We study a sample complexity vs. conditioning tradeoff in modern signal recovery problems (including sparse recovery, low-rank matrix sensing, covariance estimation, and abstract phase retrieval), where convex optimization problems are…

Optimization and Control · Mathematics 2024-07-19 Lijun Ding , Alex L. Wang

This paper studies the deflation algorithm when applied to estimate a low-rank symmetric spike contained in a large tensor corrupted by additive Gaussian noise. Specifically, we provide a precise characterization of the large-dimensional…

Machine Learning · Statistics 2023-04-21 Mohamed El Amine Seddik , José Henrique de Morais Goulart , Maxime Guillaud

In this paper, we develop new statistical theory for probabilistic principal component analysis models in high dimensions. The focus is the estimation of the noise variance, which is an important and unresolved issue when the number of…

Statistics Theory · Mathematics 2014-06-23 Damien Passemier , Zhaoyuan Li , Jian-Feng Yao

This paper concerns the problem of recovering an unknown but structured signal $x \in R^n$ from $m$ quadratic measurements of the form $y_r=|<a_r,x>|^2$ for $r=1,2,...,m$. We focus on the under-determined setting where the number of…

Machine Learning · Computer Science 2017-02-22 Mahdi Soltanolkotabi

We revisit the problem of sampling from a target distribution that has a smooth strongly log-concave density everywhere in $\mathbb R^p$. In this context, if no additional density information is available, the randomized midpoint…

Statistics Theory · Mathematics 2023-06-19 Lu Yu , Avetik Karagulyan , Arnak Dalalyan

Tensor Robust Principal Component Analysis (TRPCA) holds a crucial position in machine learning and computer vision. It aims to recover underlying low-rank structures and to characterize the sparse structures of noise. Current approaches…

Numerical Analysis · Mathematics 2026-01-15 Chao Wang , Huiwen Zheng , Raymond Chan , Youwei Wen

We study asymmetric rank-one spiked tensor models in the high-dimensional regime, where the noise entries are independent and identically distributed with zero mean, unit variance, and finite fourth moment. This extends the classical…

Statistics Theory · Mathematics 2026-03-12 Yanjin Xiang , Zhihua Zhang

In compressed sensing one uses known structures of otherwise unknown signals to recover them from as few linear observations as possible. The structure comes in form of some compressibility including different notions of sparsity and low…

Information Theory · Computer Science 2019-05-29 Martin Kliesch , Stanislaw J. Szarek , Peter Jung