English
Related papers

Related papers: Subspace Embeddings and $\ell_p$-Regression Using …

200 papers

It is known that if finite subsets of a locally finite metric space $M$ admit $C$-bilipschitz embeddings into $\ell_p$ $(1\le p\le \infty)$, then for every $\epsilon>0$, the space $M$ admits a $(C+\epsilon)$-bilipschitz embedding into…

Functional Analysis · Mathematics 2019-10-10 Sofiya Ostrovska , Mikhail I. Ostrovskii

Efficiently computing accurate representations of high-dimensional data is essential for data analysis and unsupervised learning. Dendrograms, also known as ultrametrics, are widely used representations that preserve hierarchical…

Data Structures and Algorithms · Computer Science 2025-03-18 Gabriel Bathie , Guillaume Lagarde

Near isometric orthogonal embeddings to lower dimensions are a fundamental tool in data science and machine learning. In this paper, we present the construction of such embeddings that minimizes the maximum distortion for a given set of…

Machine Learning · Statistics 2017-12-15 Kshiteej Sheth , Dinesh Garg , Anirban Dasgupta

We propose novel randomized optimization methods for high-dimensional convex problems based on restrictions of variables to random subspaces. We consider oblivious and data-adaptive subspaces and study their approximation properties via…

Information Theory · Computer Science 2020-12-15 Jonathan Lacotte , Mert Pilanci

Sparse recovery is among the most well-studied problems in learning theory and high-dimensional statistics. In this work, we investigate the statistical and computational landscapes of sparse recovery with $\ell_\infty$ error guarantees.…

Statistics Theory · Mathematics 2026-02-19 Ziyun Chen , Jerry Li , Kevin Tian , Yusong Zhu

The $\ell_p$ subspace approximation problem is an NP-hard low rank approximation problem that generalizes the median hyperplane ($p = 1$), principal component analysis ($p = 2$), and center hyperplane problems ($p = \infty$). A popular…

Data Structures and Algorithms · Computer Science 2025-04-04 David P. Woodruff , Taisuke Yasuda

We study first-order optimization algorithms under the constraint that the descent direction is quantized using a pre-specified budget of $R$-bits per dimension, where $R \in (0 ,\infty)$. We propose computationally efficient optimization…

Machine Learning · Computer Science 2022-08-17 Rajarshi Saha , Mert Pilanci , Andrea J. Goldsmith

Recent works in dimensionality reduction for regression tasks have introduced the notion of sensitivity, an estimate of the importance of a specific datapoint in a dataset, offering provable guarantees on the quality of the approximation…

Machine Learning · Computer Science 2023-11-22 Swati Padmanabhan , David P. Woodruff , Qiuyi Zhang

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

Linear regression in $\ell_p$-norm is a canonical optimization problem that arises in several applications, including sparse recovery, semi-supervised learning, and signal processing. Generic convex optimization algorithms for solving…

Data Structures and Algorithms · Computer Science 2020-01-13 Deeksha Adil , Richard Peng , Sushant Sachdeva

A matrix $M: A \times X \rightarrow \{-1,1\}$ corresponds to the following learning problem: An unknown element $x \in X$ is chosen uniformly at random. A learner tries to learn $x$ from a stream of samples, $(a_1, b_1), (a_2, b_2) \ldots$,…

Machine Learning · Computer Science 2017-08-10 Sumegha Garg , Ran Raz , Avishay Tal

Modern machine learning embeddings provide powerful compression of high-dimensional data, yet they typically destroy the geometric structure required for classical likelihood-based statistical inference. This paper develops a rigorous…

Machine Learning · Statistics 2025-12-30 Deniz Akdemir

We prove that every proper ultrametric space isometrically embeds into $\ell_p$ for any $p\geq 1$. As an application we discuss an $\ell_p$-version of nonlinear Dvoretzky's theorem.

Metric Geometry · Mathematics 2012-03-09 Kei Funano

Sparsity finds applications in areas as diverse as statistics, machine learning, and signal processing. Computations over sparse structures are less complex compared to their dense counterparts, and their storage consumes less space. This…

Signal Processing · Electrical Eng. & Systems 2023-01-31 Omar M. Sleem , M. E. Ashour , N. S. Aybat , Constantino M. Lagoa

Let X be a data matrix of rank \rho, whose rows represent n points in d-dimensional space. The linear support vector machine constructs a hyperplane separator that maximizes the 1-norm soft margin. We develop a new oblivious dimension…

Machine Learning · Computer Science 2014-04-18 Saurabh Paul , Christos Boutsidis , Malik Magdon-Ismail , Petros Drineas

Reduced model spaces, such as reduced basis and polynomial chaos, are linear spaces $V_n$ of finite dimension $n$ which are designed for the efficient approximation of families parametrized PDEs in a Hilbert space $V$. The manifold…

Numerical Analysis · Mathematics 2020-08-04 Albert Cohen , Wolfgang Dahmen , Ron DeVore , Jalal Fadili , Olga Mula , James Nichols

Motivated by the Koml\'os conjecture in combinatorial discrepancy, we study the discrepancy of random matrices with $m$ rows and $n$ independent columns drawn from a bounded lattice random variable. It is known that for $n$ tending to…

Combinatorics · Mathematics 2018-10-19 Cole Franks , Michael Saks

We prove that every $n$-point metric space of negative type (and, in particular, every $n$-point subset of $L_1$) embeds into a Euclidean space with distortion $O(\sqrt{\log n} \cdot\log \log n)$, a result which is tight up to the iterated…

Metric Geometry · Mathematics 2007-05-23 Sanjeev Arora , James R. Lee , Assaf Naor

We study the problem of testing whether a matrix $\mathbf{A} \in \mathbb{R}^{n \times n}$ with bounded entries ($\|\mathbf{A}\|_\infty \leq 1$) is positive semi-definite (PSD), or $\epsilon$-far in Euclidean distance from the PSD cone,…

Data Structures and Algorithms · Computer Science 2020-09-21 Ainesh Bakshi , Nadiia Chepurko , Rajesh Jayaram

We provide the first nearly-linear time algorithm for approximating $\ell_{q \rightarrow p}$-norms of non-negative matrices, for $q \geq p \geq 1$. Our algorithm returns a $(1-\varepsilon)$-approximation to the matrix norm in time…

Data Structures and Algorithms · Computer Science 2025-03-26 Étienne Objois , Adrian Vladu
‹ Prev 1 3 4 5 6 7 10 Next ›