English
Related papers

Related papers: New and improved Johnson-Lindenstrauss embeddings …

200 papers

We establish theoretical recovery guarantees of a family of Riemannian optimization algorithms for low rank matrix recovery, which is about recovering an $m\times n$ rank $r$ matrix from $p < mn$ number of linear measurements. The…

Numerical Analysis · Mathematics 2016-04-12 Ke Wei , Jian-Feng Cai , Tony F. Chan , Shingyu Leung

We consider low-distortion embeddings for subspaces under \emph{entrywise nonlinear transformations}. In particular we seek embeddings that preserve the norm of all vectors in a space $S = \{y: y = f(x)\text{ for }x \in Z\}$, where $Z$ is a…

Machine Learning · Computer Science 2020-10-09 Aarshvi Gajjar , Cameron Musco

We consider the problem of efficient randomized dimensionality reduction with norm-preservation guarantees. Specifically we prove data-dependent Johnson-Lindenstrauss-type geometry preservation guarantees for Ho's random subspace method:…

Machine Learning · Statistics 2017-05-19 Nick Lim , Robert J. Durrant

Metric embedding has become a common technique in the design of algorithms. Its applicability is often dependent on how high the embedding's distortion is. For example, embedding finite metric space into trees may require linear distortion…

Data Structures and Algorithms · Computer Science 2007-05-23 Yair Bartal , Manor Mendel

The famous Johnson-Lindenstrauss lemma states that for any set of n vectors, there is a linear transformation into a space of dimension O(log n) that approximately preserves all their lengths. In fact, a Haar random unitary transformation…

Quantum Physics · Physics 2018-07-25 Pranab Sen

The matrix $A:\mathbb{R}^n \to \mathbb{R}^m$ is $(\delta,k)$-regular if for any $k$-sparse vector $x$, $$ \left| \|Ax\|_2^2-\|x\|_2^2\right| \leq \delta \sqrt{k} \|x\|_2^2. $$ We show that if $A$ is $(\delta,k)$-regular for $1 \leq k \leq…

Statistics Theory · Mathematics 2021-03-10 Shahar Mendelson

Johnson and Lindenstrauss (Contemporary Mathematics, 1984) showed that for $n > m$, a scaled random projection $\mathbf{A}$ from $\mathbb{R}^n$ to $\mathbb{R}^m$ is an approximate isometry on any set $S$ of size at most exponential in $m$.…

Computation · Statistics 2025-04-15 Andrej Bogdanov , Alon Rosen , Neekon Vafa , Vinod Vaikuntanathan

We study the Riemannian optimization methods on the embedded manifold of low rank matrices for the problem of matrix completion, which is about recovering a low rank matrix from its partial entries. Assume $m$ entries of an $n\times n$ rank…

Numerical Analysis · Mathematics 2016-04-12 Ke Wei , Jian-Feng Cai , Tony F. Chan , Shingyu Leung

The seminal Fast Johnson-Lindenstrauss (Fast JL) transform by Ailon and Chazelle (SICOMP'09) embeds a set of $n$ points in $d$-dimensional Euclidean space into optimal $k=O(\varepsilon^{-2} \ln n)$ dimensions, while preserving all pairwise…

Data Structures and Algorithms · Computer Science 2022-04-06 Ora Nova Fandina , Mikael Møller Høgsgaard , Kasper Green Larsen

We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the…

Machine Learning · Statistics 2018-09-05 Krzysztof Choromanski , Mark Rowland , Adrian Weller

We prove a variant of a Johnson-Lindenstrauss lemma for matrices with circulant structure. This approach allows to minimise the randomness used, is easy to implement and provides good running times. The price to be paid is the higher…

Functional Analysis · Mathematics 2010-01-28 Aicke Hinrichs , Jan Vybíral

The restricted isometry property (RIP) is an important matrix condition in compressed sensing, but the best matrix constructions to date use randomness. This paper leverages pseudorandom properties of the Legendre symbol to reduce the…

Combinatorics · Mathematics 2014-06-17 Afonso S. Bandeira , Matthew Fickus , Dustin G. Mixon , Joel Moreira

We study constructions of $k \times n$ matrices $A$ that both (1) satisfy the restricted isometry property (RIP) at sparsity $s$ with optimal parameters, and (2) are efficient in the sense that only $O(n\log n)$ operations are required to…

Numerical Analysis · Computer Science 2013-02-19 Nir Ailon , Holger Rauhut

Can the behavior of a random matrix be improved by modifying a small fraction of its entries? Consider a random matrix $A$ with i.i.d. entries. We show that the operator norm of $A$ can be reduced to the optimal order $O(\sqrt{n})$ by…

Probability · Mathematics 2017-11-02 Elizaveta Rebrova , Roman Vershynin

Motivated by the problem of compressing point sets into as few bits as possible while maintaining information about approximate distances between points, we construct random nonlinear maps $\varphi_\ell$ that compress point sets in the…

Computational Geometry · Computer Science 2024-03-05 Brett Leroux , Luis Rademacher

The Restricted Isometry Property (RIP) is a fundamental property of a matrix enabling sparse recovery. Informally, an m x n matrix satisfies RIP of order k in the l_p norm if ||Ax||_p \approx ||x||_p for any vector x that is k-sparse, i.e.,…

Data Structures and Algorithms · Computer Science 2014-04-29 Piotr Indyk , Ilya Razenshteyn

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

Structures play a significant role in the field of signal processing. As a representative of structural data, low rank matrix along with its restricted isometry property (RIP) has been an important research topic in compressive signal…

Information Theory · Computer Science 2015-06-23 Xinyue Shen , Yuantao Gu

We consider the problem of learning a low-rank matrix, constrained to lie in a linear subspace, and introduce a novel factorization for modeling such matrices. A salient feature of the proposed factorization scheme is it decouples the…

Machine Learning · Statistics 2018-06-18 Pratik Jawanpuria , Bamdev Mishra

Let $\varepsilon\in(0,1)$ and $X\subset\mathbb R^d$ be arbitrary with $|X|$ having size $n>1$. The Johnson-Lindenstrauss lemma states there exists $f:X\rightarrow\mathbb R^m$ with $m = O(\varepsilon^{-2}\log n)$ such that $$ \forall x\in X\…

Data Structures and Algorithms · Computer Science 2018-10-23 Shyam Narayanan , Jelani Nelson