English
Related papers

Related papers: Low-distortion Subspace Embeddings in Input-sparsi…

200 papers

We show an analog to the Fast Johnson-Lindenstrauss Transform for Nearest Neighbor Preserving Embeddings in $\ell_2$. These are sparse, randomized embeddings that preserve the (approximate) nearest neighbors. The dimensionality of the…

Data Structures and Algorithms · Computer Science 2017-07-24 Johan Sivertsen

In this paper, we study a fast approximation method for {\it large-scale high-dimensional} sparse least-squares regression problem by exploiting the Johnson-Lindenstrauss (JL) transforms, which embed a set of high-dimensional vectors into a…

Statistics Theory · Mathematics 2015-07-21 Tianbao Yang , Lijun Zhang , Qihang Lin , Rong Jin

We show that for every large enough integer $N$, there exists an $N$-point subset of $L_1$ such that for every $D>1$, embedding it into $\ell_1^d$ with distortion $D$ requires dimension $d$ at least $N^{\Omega(1/D^2)}$, and that for every…

Metric Geometry · Mathematics 2011-12-22 Oded Regev

Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification. Retrieval of such representations from a large database is however computationally challenging.…

Machine Learning · Computer Science 2020-04-14 Biswajit Paria , Chih-Kuan Yeh , Ian E. H. Yen , Ning Xu , Pradeep Ravikumar , Barnabás Póczos

We construct a matrix $M\in R^{m\otimes d^c}$ with just $m=O(c\,\lambda\,\varepsilon^{-2}\text{poly}\log1/\varepsilon\delta)$ rows, which preserves the norm $\|Mx\|_2=(1\pm\varepsilon)\|x\|_2$ of all $x$ in any given $\lambda$ dimensional…

Data Structures and Algorithms · Computer Science 2019-09-05 Thomas D. Ahle , Jakob B. T. Knudsen

We demonstrate an equivalence between reproducing kernel Hilbert space (RKHS) embeddings of conditional distributions and vector-valued regressors. This connection introduces a natural regularized loss function which the RKHS embeddings…

Machine Learning · Computer Science 2012-07-25 Steffen Grünewälder , Guy Lever , Luca Baldassarre , Sam Patterson , Arthur Gretton , Massimilano Pontil

We propose computationally efficient encoders and decoders for lossy compression using a Sparse Regression Code. The codebook is defined by a design matrix and codewords are structured linear combinations of columns of this matrix. The…

Information Theory · Computer Science 2014-05-20 Ramji Venkataramanan , Tuhin Sarkar , Sekhar Tatikonda

Rod-based structures are commonly used in practical applications in science and engineering. However, in many design, analysis, and manufacturing tasks, handling the rod-based structures in three dimensions directly is generally…

Computational Geometry · Computer Science 2026-02-10 Mark Yan Lok Yip , Gary P. T. Choi

Bilipschitz invariant theory concerns low-distortion embeddings of orbit spaces into Euclidean space. To date, embeddings with the smallest-possible distortion are known for only a few cases, to include: (a) planar rotations, (b) real phase…

Functional Analysis · Mathematics 2026-03-26 Jameson Cahill , Joseph W. Iverson , Dustin G. Mixon , Nathan Willey

Under which conditions and with which distortions can we preserve the pairwise-distances of low-complexity vectors, e.g., for structured sets such as the set of sparse vectors or the one of low-rank matrices, when these are mapped in a…

Information Theory · Computer Science 2016-11-15 Laurent Jacques

Consider the empirical risk minimization (ERM) problem, which is stated as follows. Let $K_1, \dots, K_m$ be compact convex sets with $K_i \subseteq \mathbb{R}^{n_i}$ for $i \in [m]$, $n = \sum_{i=1}^m n_i$, and $n_i\le C_K$ for some…

Data Structures and Algorithms · Computer Science 2025-12-02 Yang P. Liu , Richard Peng , Colin Tang , Albert Weng , Junzhao Yang

Low-rank approximation is a common tool used to accelerate kernel methods: the $n \times n$ kernel matrix $K$ is approximated via a rank-$k$ matrix $\tilde K$ which can be stored in much less space and processed more quickly. In this work…

Data Structures and Algorithms · Computer Science 2017-11-07 Cameron Musco , David P. Woodruff

We give the first non-trivial decremental dynamic embedding of a weighted, undirected graph $G$ into $\ell_p$ space. Given a weighted graph $G$ undergoing a sequence of edge weight increases, the goal of this problem is to maintain a…

Data Structures and Algorithms · Computer Science 2024-08-15 Kiarash Banihashem , MohammadTaghi Hajiaghayi , Dariusz R. Kowalski , Jan Olkowski , Max Springer

We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels. Given a sufficiently large (polynomial-size) training set drawn i.i.d. from…

Machine Learning · Computer Science 2020-06-05 Adam Klivans , Pravesh K. Kothari , Raghu Meka

We give a simple algorithm to efficiently sample the rows of a matrix while preserving the p-norms of its product with vectors. Given an $n$-by-$d$ matrix $\boldsymbol{\mathit{A}}$, we find with high probability and in input sparsity time…

Data Structures and Algorithms · Computer Science 2014-12-02 Michael B. Cohen , Richard Peng

A common technique for compressing a neural network is to compute the $k$-rank $\ell_2$ approximation $A_{k,2}$ of the matrix $A\in\mathbb{R}^{n\times d}$ that corresponds to a fully connected layer (or embedding layer). Here, $d$ is the…

Machine Learning · Computer Science 2020-09-29 Murad Tukan , Alaa Maalouf , Matan Weksler , Dan Feldman

A major open problem in the field of metric embedding is the existence of dimension reduction for $n$-point subsets of Euclidean space, such that both distortion and dimension depend only on the {\em doubling constant} of the pointset, and…

Computational Geometry · Computer Science 2013-08-26 Yair Bartal , Lee-Ad Gottlieb , Ofer Neiman

We present a relation between sparsity and non-Euclidean isomorphic embeddings. We introduce a general restricted isomorphism property and show how it enables to construct embeddings of $\ell_p^n$, $p > 0$, into various type of Banach or…

Functional Analysis · Mathematics 2011-07-07 Omer Friedland , Olivier Guédon

We introduce the first iterative algorithm for constructing a $\varepsilon$-coreset that guarantees deterministic $\ell_p$ subspace embedding for any $p \in [1,\infty)$ and any $\varepsilon > 0$. For a given full rank matrix $\mathbf{X} \in…

Data Structures and Algorithms · Computer Science 2026-05-18 Rachit Chhaya , Anirban Dasgupta , Dan Feldman , Supratim Shit

We study beyond worst-case dimensionality reduction for $s$-sparse vectors. Our work is divided into two parts, each focusing on a different facet of beyond worst-case analysis: We first consider average-case guarantees. A folklore upper…

Data Structures and Algorithms · Computer Science 2025-02-28 Sandeep Silwal , David P. Woodruff , Qiuyi Zhang