English
Related papers

Related papers: Optimal Embedding Dimension for Sparse Subspace Em…

200 papers

Despite many applications, dimensionality reduction in the $\ell_1$-norm is much less understood than in the Euclidean norm. We give two new oblivious dimensionality reduction techniques for the $\ell_1$-norm which improve exponentially…

Data Structures and Algorithms · Computer Science 2021-08-09 Yi Li , David P. Woodruff , Taisuke Yasuda

We consider the problem of estimating a $d$-dimensional $s$-sparse discrete distribution from its samples observed under a $b$-bit communication constraint. The best-known previous result on $\ell_2$ estimation error for this problem is…

Machine Learning · Statistics 2021-06-17 Wei-Ning Chen , Peter Kairouz , Ayfer Özgür

The aim of this paper is two-fold: firstly, to present subspace embedding properties for $s$-hashing sketching matrices, with $s\geq 1$, that are optimal in the projection dimension $m$ of the sketch, namely, $m=\mathcal{O}(d)$, where $d$…

Numerical Analysis · Mathematics 2021-05-26 Coralia Cartis , Jan Fiala , Zhen Shao

Spectral embedding based on the Singular Value Decomposition (SVD) is a widely used "preprocessing" step in many learning tasks, typically leading to dimensionality reduction by projecting onto a number of dominant singular vectors and…

Machine Learning · Statistics 2015-09-29 Dinesh Ramasamy , Upamanyu Madhow

We give a fast oblivious L2-embedding of $A\in \mathbb{R}^{n x d}$ to $B\in \mathbb{R}^{r x d}$ satisfying $(1-\varepsilon)\|A x\|_2^2 \le \|B x\|_2^2 <= (1+\varepsilon) \|Ax\|_2^2.$ Our embedding dimension $r$ equals $d$, a constant…

Machine Learning · Computer Science 2019-09-30 Malik Magdon-Ismail , Alex Gittens

We describe a probabilistic, {\it sublinear} runtime, measurement-optimal system for model-based sparse recovery problems through dimensionality reducing, {\em dense} random matrices. Specifically, we obtain a linear sketch $u\in \R^M$ of a…

Information Theory · Computer Science 2012-06-22 Anastasios Kyrillidis , Volkan Cevher

We give two different and simple constructions for dimensionality reduction in $\ell_2$ via linear mappings that are sparse: only an $O(\varepsilon)$-fraction of entries in each column of our embedding matrices are non-zero to achieve…

Data Structures and Algorithms · Computer Science 2014-02-07 Daniel M. Kane , Jelani Nelson

We consider a generalization of the classic linear regression problem to the case when the loss is an Orlicz norm. An Orlicz norm is parameterized by a non-negative convex function $G:\mathbb{R}_+\rightarrow\mathbb{R}_+$ with $G(0)=0$: the…

Data Structures and Algorithms · Computer Science 2018-06-19 Alexandr Andoni , Chengyu Lin , Ying Sheng , Peilin Zhong , Ruiqi Zhong

Is it possible to find the sparsest vector (direction) in a generic subspace $\mathcal{S} \subseteq \mathbb{R}^p$ with $\mathrm{dim}(\mathcal{S})= n < p$? This problem can be considered a homogeneous variant of the sparse recovery problem,…

Information Theory · Computer Science 2016-09-21 Qing Qu , Ju Sun , John Wright

Sparse linear regression is one of the most basic questions in machine learning and statistics. Here, we are given as input a design matrix $X \in \mathbb{R}^{N \times d}$ and measurements or labels ${y} \in \mathbb{R}^N$ where ${y} = {X}…

Machine Learning · Computer Science 2025-11-11 Gautam Chandrasekaran , Raghu Meka , Konstantinos Stavropoulos

Dense embedding models are commonly deployed in commercial search engines, wherein all the document vectors are pre-computed, and near-neighbor search (NNS) is performed with the query vector to find relevant documents. However, the…

Machine Learning · Computer Science 2020-09-01 Tharun Medini , Beidi Chen , Anshumali Shrivastava

We design a new distribution over $\poly(r \eps^{-1}) \times n$ matrices $S$ so that for any fixed $n \times d$ matrix $A$ of rank $r$, with probability at least 9/10, $\norm{SAx}_2 = (1 \pm \eps)\norm{Ax}_2$ simultaneously for all $x \in…

Data Structures and Algorithms · Computer Science 2013-04-08 Kenneth L. Clarkson , David P. Woodruff

In this paper, we consider a compressed sensing problem of reconstructing a sparse signal from an undersampled set of noisy linear measurements. The regularized least squares or least absolute shrinkage and selection operator (LASSO)…

Information Theory · Computer Science 2014-10-30 Chao-Kai Wen , Jun Zhang , Kai-Kit Wong , Jung-Chieh Chen , Chau Yuen

In this note we discuss a common misconception, namely that embeddings are always used to reduce the dimensionality of the item space. We show that when we measure dimensionality in terms of information entropy then the embedding of sparse…

Machine Learning · Computer Science 2019-01-09 Maxim Naumov

We prove, using the subspace embedding guarantee in a black box way, that one can achieve the spectral norm guarantee for approximate matrix multiplication with a dimensionality-reducing map having $m = O(\tilde{r}/\varepsilon^2)$ rows.…

Data Structures and Algorithms · Computer Science 2016-03-03 Michael B. Cohen , Jelani Nelson , David P. Woodruff

Why does the low dimensionality of representations, typically $d\approx 1000$, not prevent modern embedding-based retrieval models from scaling to billions, or even trillions, of data points? To answer this question, we study maximal-margin…

Machine Learning · Computer Science 2026-05-25 Kiril Bangachev , Guy Bresler , Jonathan Kogan , Yury Polyanskiy

An approximate sparse recovery system in ell_1 norm formally consists of parameters N, k, epsilon an m-by-N measurement matrix, Phi, and a decoding algorithm, D. Given a vector, x, where x_k denotes the optimal k-term approximation to x,…

Data Structures and Algorithms · Computer Science 2011-07-15 Ely Porat , Martin J. Strauss

Given $n$ noisy samples with $p$ dimensions, where $n \ll p$, we show that the multi-step thresholding procedure based on the Lasso -- we call it the {\it Thresholded Lasso}, can accurately estimate a sparse vector $\beta \in {\mathbb R}^p$…

Statistics Theory · Mathematics 2025-10-28 Shuheng Zhou

This paper develops a new method for recovering m-sparse signals that is simultaneously uniform and quick. We present a reconstruction algorithm whose run time, O(m log^2(m) log^2(d)), is sublinear in the length d of the signal. The…

Data Structures and Algorithms · Computer Science 2007-05-23 A. C. Gilbert , M. J. Strauss , J. A. Tropp , R. Vershynin

We propose a probabilistic framework for interpreting and developing hard thresholding sparse signal reconstruction methods and present several new algorithms based on this framework. The measurements follow an underdetermined linear model,…

Information Theory · Computer Science 2010-11-08 Kun Qiu , Aleksandar Dogandzic