English
Related papers

Related papers: Sparse Dimensionality Reduction Revisited

200 papers

The $l_2$ flattening lemma of Johnson and Lindenstrauss [JL84] is a powerful tool for dimension reduction. It has been conjectured that the target dimension bounds can be refined and bounded in terms of the intrinsic dimensionality of the…

Computational Geometry · Computer Science 2015-06-09 Lee-Ad Gottlieb , Robert Krauthgamer

Sparsity is a basic property of real vectors that is exploited in a wide variety of applications. In this work, we describe property testing algorithms for sparsity that observe a low-dimensional projection of the input. We consider two…

Data Structures and Algorithms · Computer Science 2017-09-14 Siddharth Barman , Arnab Bhattacharyya , Suprovat Ghoshal

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

We study the support recovery problem for compressed sensing, where the goal is to reconstruct the a high-dimensional $K$-sparse signal $\mathbf{x}\in\mathbb{R}^N$, from low-dimensional linear measurements with and without noise. Our key…

Information Theory · Computer Science 2018-02-27 Xiao Li , Dong Yin , Sameer Pawar , Ramtin Pedarsani , Kannan Ramchandran

The sparse matrix compression problem asks for a one-dimensional representation of a binary $n \times \ell$ matrix, formed by an integer array of row indices and a shift function for each row, such that accessing a matrix entry is possible…

Data Structures and Algorithms · Computer Science 2026-02-18 Vincent Jugé , Dominik Köppl , Vincent Limouzy , Andrea Marino , Jannik Olblich , Giulia Punzi , Takeaki Uno

In this paper, we investigate optimization problems with nonnegative and orthogonal constraints, where any feasible matrix of size $n \times p$ exhibits a sparsity pattern such that each row accommodates at most one nonzero entry. Our…

Optimization and Control · Mathematics 2025-11-06 Lei Wang , Xin Liu , Xiaojun Chen

Feature hashing and other random projection schemes are commonly used to reduce the dimensionality of feature vectors. The goal is to efficiently project a high-dimensional feature vector living in $\mathbb{R}^n$ into a much…

Machine Learning · Statistics 2020-03-27 Meena Jagadeesan

In many practical applications it is important to build symmetries into neural network architectures. Consider the important case of permutation symmetry on point clouds consisting of $n$ points in $d$ dimensions. In this case the network…

Machine Learning · Computer Science 2026-05-12 Ali Syed , Aditya Nambiar , Jonathan W. Siegel

In this paper we make a novel use of the Johnson-Lindenstrauss Lemma. The Lemma has an existential form saying that there exists a JL transformation $f$ of the data points into lower dimensional space such that all of them fall into…

Data Structures and Algorithms · Computer Science 2017-11-10 Mieczysław A. Kłopotek

It is difficult to find the optimal sparse solution of a manifold learning based dimensionality reduction algorithm. The lasso or the elastic net penalized manifold learning based dimensionality reduction is not directly a lasso penalized…

Machine Learning · Computer Science 2010-07-28 Tianyi Zhou , Dacheng Tao , Xindong Wu

Our work is focused on the joint sparsity recovery problem where the common sparsity pattern is corrupted by Poisson noise. We formulate the confidence-constrained optimization problem in both least squares (LS) and maximum likelihood (ML)…

Machine Learning · Statistics 2013-10-10 E. Chunikhina , R. Raich , T. Nguyen

As its name suggests, sufficient dimension reduction (SDR) targets to estimate a subspace from data that contains all information sufficient to explain a dependent variable. Ample approaches exist to SDR, some of the most recent of which…

Methodology · Statistics 2020-12-15 Emmanuel Jordy Menvouta , Sven Serneels , Tim Verdonck

We consider sparse variants of the classical Learning Parities with random Noise (LPN) problem. Our main contribution is a new algorithmic framework that provides learning algorithms against low-noise for both Learning Sparse Parities…

Cryptography and Security · Computer Science 2025-06-03 Xue Chen , Wenxuan Shu , Zhaienhe Zhou

Metric embeddings into structured spaces, particularly hierarchically well-separated trees (HSTs), are a fundamental tool in the design of online algorithms. In the classical online embedding setting, points arrive sequentially and must be…

Data Structures and Algorithms · Computer Science 2026-05-13 Christian Coester , Yichen Huang

Previous studies yielded discouraging results for item-level locally differentially private linear regression with $s^*$-sparsity assumption, where the minimax rate for $nm$ samples is $\mathcal{O}(s^{*}d / nm\varepsilon^2)$. This can be…

Machine Learning · Statistics 2024-08-09 Yuheng Ma , Ke Jia , Hanfang Yang

Recovery of the sparsity pattern (or support) of an unknown sparse vector from a small number of noisy linear measurements is an important problem in compressed sensing. In this paper, the high-dimensional setting is considered. It is shown…

Information Theory · Computer Science 2013-02-06 Galen Reeves , Michael Gastpar

We study a new class of codes for lossy compression with the squared-error distortion criterion, designed using the statistical framework of high-dimensional linear regression. Codewords are linear combinations of subsets of columns of a…

Information Theory · Computer Science 2015-12-21 Ramji Venkataramanan , Antony Joseph , Sekhar Tatikonda

Many real-world data sets are sparse or almost sparse. One method to measure this for a matrix $A\in \mathbb{R}^{n\times n}$ is the \emph{numerical sparsity}, denoted $\mathsf{ns}(A)$, defined as the minimum $k\geq 1$ such that…

Data Structures and Algorithms · Computer Science 2021-07-06 Vladimir Braverman , Robert Krauthgamer , Aditya Krishnan , Shay Sapir

The celebrated Johnson-Lindenstrauss lemma states that for all $\varepsilon \in (0,1)$ and finite sets $X \subseteq \mathbb{R}^N$ with $n>1$ elements, there exists a matrix $\Phi \in \mathbb{R}^{m \times N}$ with…

Metric Geometry · Mathematics 2024-03-08 Rafael Chiclana , Mark A. Iwen , Mark Philip Roach

We investigate the reconstruction of multivariate functions from samples using sparse recovery techniques. For Square Root Lasso, Orthogonal Matching Pursuit, and Compressive Sampling Matching Pursuit, we demonstrate both theoretically and…

Numerical Analysis · Mathematics 2026-01-21 Moritz Moeller , Sebastian Neumayer , Kateryna Pozharska , Tizian Sommerfeld , Tino Ullrich