English
Related papers

Related papers: The Fast Convergence of Incremental PCA

200 papers

We study robust PCA for the fully observed setting, which is about separating a low rank matrix $\boldsymbol{L}$ and a sparse matrix $\boldsymbol{S}$ from their sum $\boldsymbol{D}=\boldsymbol{L}+\boldsymbol{S}$. In this paper, a new…

Information Theory · Computer Science 2021-06-29 HanQin Cai , Jian-Feng Cai , Ke Wei

L\'evy's Upward Theorem says that the conditional expectation of an integrable random variable converges with probability one to its true value with increasing information. In this paper, we use methods from effective probability theory to…

Logic · Mathematics 2024-06-04 Simon M. Huttegger , Sean Walsh , Francesca Zaffora Blando

We study attention mechanisms through the lens of a canonical unsupervised problem: principal component analysis (PCA). We show that, when trained on Gaussian data, both softmax and linear attention layers learn parameters that align with…

Optimization and Control · Mathematics 2026-05-19 Rodrigo Maulen-Soto , Claire Boyer

Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature…

Machine Learning · Statistics 2022-06-14 Bharath Sriperumbudur , Nicholas Sterge

The problem of estimating sparse eigenvectors of a symmetric matrix attracts a lot of attention in many applications, especially those with high dimensional data set. While classical eigenvectors can be obtained as the solution of a…

Machine Learning · Statistics 2016-11-03 Konstantinos Benidis , Ying Sun , Prabhu Babu , Daniel P. Palomar

Several fundamental tasks in data science rely on computing an extremal eigenspace of size $r \ll n$, where $n$ is the underlying problem dimension. For example, spectral clustering and PCA both require the computation of the leading…

Numerical Analysis · Mathematics 2019-09-04 Vasileios Charisopoulos , Austin R. Benson , Anil Damle

We present a new algorithm for clustering points in R^n. The key property of the algorithm is that it is affine-invariant, i.e., it produces the same partition for any affine transformation of the input. It has strong guarantees when the…

Machine Learning · Computer Science 2008-08-04 S. Charles Brubaker , Santosh S. Vempala

We introduce a variant of (sparse) PCA in which the set of feasible support sets is determined by a graph. In particular, we consider the following setting: given a directed acyclic graph $G$ on $p$ vertices corresponding to variables, the…

Independent Component Analysis (ICA) recently has attracted attention in the statistical literature as an alternative to elliptical models. Whereas k-dimensional elliptical densities depend on one single unspecified radial density, however,…

Methodology · Statistics 2013-12-17 Marc Hallin , Chintan Mehta

We study the problem of estimating the covariance matrix of a high-dimensional distribution when a small constant fraction of the samples can be arbitrarily corrupted. Recent work gave the first polynomial time algorithms for this problem…

Machine Learning · Computer Science 2019-06-12 Yu Cheng , Ilias Diakonikolas , Rong Ge , David Woodruff

We study distributed principal component analysis (PCA) in high-dimensional settings under the spiked model. In such regimes, sample eigenvectors can deviate significantly from population ones, introducing a persistent bias. Existing…

Methodology · Statistics 2025-05-29 Weiming Li , Zeng Li , Siyu Wang , Yanqing Yin , Junpeng Zhu

We propose a novel statistical inference framework for streaming principal component analysis (PCA) using Oja's algorithm, enabling the construction of confidence intervals for individual entries of the estimated eigenvector. Most existing…

Statistics Theory · Mathematics 2025-07-22 Syamantak Kumar , Shourya Pandey , Purnamrita Sarkar

We give faster algorithms and improved sample complexities for estimating the top eigenvector of a matrix $\Sigma$ -- i.e. computing a unit vector $x$ such that $x^T \Sigma x \ge (1-\epsilon)\lambda_1(\Sigma)$: Offline Eigenvector…

Data Structures and Algorithms · Computer Science 2016-05-30 Dan Garber , Elad Hazan , Chi Jin , Sham M. Kakade , Cameron Musco , Praneeth Netrapalli , Aaron Sidford

Principal component analysis (PCA) is a classical method for dimensionality reduction based on extracting the dominant eigenvectors of the sample covariance matrix. However, PCA is well known to behave poorly in the ``large $p$, small $n$''…

Statistics Theory · Mathematics 2009-08-26 Arash A. Amini , Martin J. Wainwright

We consider the problem of Robust PCA in the fully and partially observed settings. Without corruptions, this is the well-known matrix completion problem. From a statistical standpoint this problem has been recently well-studied, and…

Information Theory · Computer Science 2016-09-20 Xinyang Yi , Dohyung Park , Yudong Chen , Constantine Caramanis

In this paper we present a convergence rate analysis of inexact variants of several randomized iterative methods. Among the methods studied are: stochastic gradient descent, stochastic Newton, stochastic proximal point and stochastic…

Optimization and Control · Mathematics 2019-03-20 Nicolas Loizou , Peter Richtárik

The Iterative Rational Krylov Algorithm (IRKA) of [8] is an interpolatory model reduction approach to the optimal $\mathcal{H}_2$ approximation problem. Even though the method has been illustrated to show rapid convergence in various…

Numerical Analysis · Mathematics 2013-01-23 Garret Flagg , Christopher Beattie , Serkan Gugercin

We consider estimation procedures which are recursive in the sense that each successive estimator is obtained from the previous one by a simple adjustment. We study rate of convergence of recursive estimation procedures for the general…

Statistics Theory · Mathematics 2007-05-23 Teo Sharia

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

Stochastic optimization naturally arises in machine learning. Efficient algorithms with provable guarantees, however, are still largely missing, when the objective function is nonconvex and the data points are dependent. This paper studies…

Machine Learning · Computer Science 2018-10-02 Minshuo Chen , Lin Yang , Mengdi Wang , Tuo Zhao