English
Related papers

Related papers: Convergence and Rate Analysis of Neural Networks f…

200 papers

Principal component analysis (PCA) is a classical and ubiquitous method for reducing data dimensionality, but it is suboptimal for heterogeneous data that are increasingly common in modern applications. PCA treats all samples uniformly so…

Statistics Theory · Mathematics 2021-12-02 David Hong , Kyle Gilman , Laura Balzano , Jeffrey A. Fessler

This work focuses on a class of general decentralized constraint-coupled optimization problems. We propose a novel nested primal-dual gradient algorithm (NPGA), which can achieve linear convergence under the weakest known condition, and its…

Optimization and Control · Mathematics 2025-05-06 Jingwang Li , Housheng Su

We present a unified theoretical framework for parametric low-rank approximation, a research area devoted to the development of efficient algorithms that act as adaptive alternatives of traditional methods such as Singular Value…

Numerical Analysis · Mathematics 2025-09-22 Nicola Rares Franco

Recently, the decentralized optimization problem is attracting growing attention. Most existing methods are deterministic with high per-iteration cost and have a convergence rate quadratically depending on the problem condition number.…

Machine Learning · Statistics 2018-05-28 Zebang Shen , Aryan Mokhtari , Tengfei Zhou , Peilin Zhao , Hui Qian

Sparse Principal Component Analysis (SPCA) is an important technique for high-dimensional data analysis, improving interpretability by imposing sparsity on principal components. However, existing methods often fail to simultaneously…

Machine Learning · Computer Science 2026-03-03 Difei Cheng , Qiao Hu

This work develops a sparse and outlier-insensitive method to fit a one-dimensional subspace that can be used as a replacement for eigenvector methods such as principal component analysis (PCA). The method is insensitive to outlier…

Optimization and Control · Mathematics 2023-01-26 Xiao Ling , J. Paul Brooks

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

It is well known that Sparse PCA (Sparse Principal Component Analysis) is NP-hard to solve exactly on worst-case instances. What is the complexity of solving Sparse PCA approximately? Our contributions include: 1) a simple and efficient…

Machine Learning · Statistics 2015-07-22 Siu On Chan , Dimitris Papailiopoulos , Aviad Rubinstein

We introduce a method for sparsifying distributed algorithms and exhibit how it leads to improvements that go past known barriers in two algorithmic settings of large-scale graph processing: Massively Parallel Computation (MPC), and Local…

Data Structures and Algorithms · Computer Science 2018-07-18 Mohsen Ghaffari , Jara Uitto

The low-rank matrix approximation problem with respect to the component-wise $\ell_1$-norm ($\ell_1$-LRA), which is closely related to robust principal component analysis (PCA), has become a very popular tool in data mining and machine…

Machine Learning · Computer Science 2018-12-19 Nicolas Gillis , Stephen A. Vavasis

This paper provides a non-asymptotic analysis of linear stochastic approximation (LSA) algorithms with fixed stepsize. This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear…

Machine Learning · Statistics 2021-06-03 Alain Durmus , Eric Moulines , Alexey Naumov , Sergey Samsonov , Kevin Scaman , Hoi-To Wai

We use deep sparsely connected neural networks to measure the complexity of a function class in $L^2(\mathbb R^d)$ by restricting connectivity and memory requirement for storing the neural networks. We also introduce representation system -…

Machine Learning · Computer Science 2021-08-17 Khay Boon Hong

Exposure correction methods aim to adjust the luminance while maintaining other luminance-unrelated information. However, current exposure correction methods have difficulty in fully separating luminance-related and luminance-unrelated…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Jingchao Peng , Thomas Bashford-Rogers , Jingkun Chen , Haitao Zhao , Zhengwei Hu , Kurt Debattista

Kernel methods provide an elegant framework for developing nonlinear learning algorithms from simple linear methods. Though these methods have superior empirical performance in several real data applications, their usefulness is inhibited…

Machine Learning · Statistics 2021-05-20 Nicholas Sterge , Bharath Sriperumbudur

Sparse PCA is one of the most well-studied problems in high-dimensional statistics. In this problem, we are given samples from a distribution with covariance $\Sigma$, whose top eigenvector $v \in R^d$ is $s$-sparse. Existing sparse PCA…

Machine Learning · Statistics 2026-03-04 Syamantak Kumar , Purnamrita Sarkar , Kevin Tian , Peiyuan Zhang

Classical canonical correlation analysis (CCA) requires matrices to be low dimensional, i.e. the number of features cannot exceed the sample size. Recent developments in CCA have mainly focused on the high-dimensional setting, where the…

Methodology · Statistics 2021-06-09 Wenjia Wang , Yi-Hui Zhou

Probabilistic Component Latent Analysis (PLCA) is a statistical modeling method for feature extraction from non-negative data. It has been fruitfully applied to various research fields of information retrieval. However, the EM-solved…

Methodology · Statistics 2017-03-16 D. Cazau , G. Nuel

Sparse coding algorithms are about finding a linear basis in which signals can be represented by a small number of active (non-zero) coefficients. Such coding has many applications in science and engineering and is believed to play an…

Neural and Evolutionary Computing · Computer Science 2016-08-14 András Lőrincz , Zsolt Palotai , Gábor Szirtes

The Soft Happy Colouring (SHC) problem, a mathematical framework for identifying homophilic network structures, seeks to maximise the number of $\rho$-happy vertices, i.e. vertices with at least a proportion $\rho$ of neighbours that share…

Social and Information Networks · Computer Science 2026-04-15 Mohammad Hadi Shekarriz , Asef Nazari , Dhananjay Thiruvady

Canonical Correlation Analysis (CCA) is a widely used spectral technique for finding correlation structures in multi-view datasets. In this paper, we tackle the problem of large scale CCA, where classical algorithms, usually requiring…

Machine Learning · Statistics 2015-06-29 Zhuang Ma , Yichao Lu , Dean Foster