English
Related papers

Related papers: Optimality of the Johnson-Lindenstrauss Dimensiona…

200 papers

This paper investigates theoretical properties of subsampling and hashing as tools for approximate Euclidean norm-preserving embeddings for vectors with (unknown) additive Gaussian noises. Such embeddings are sometimes called…

Data Structures and Algorithms · Computer Science 2022-09-05 Zhen Shao

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

Recently, learned image compression schemes have achieved remarkable improvements in image fidelity (e.g., PSNR and MS-SSIM) compared to conventional hybrid image coding ones due to their high-efficiency non-linear transform, end-to-end…

Image and Video Processing · Electrical Eng. & Systems 2023-03-09 Feng Ding , Jian Jin , Lili Meng , Weisi Lin

In this paper new general modewise Johnson-Lindenstrauss (JL) subspace embeddings are proposed that are both considerably faster to generate and easier to store than traditional JL embeddings when working with extremely large vectors and/or…

Numerical Analysis · Mathematics 2020-12-18 M. A. Iwen , D. Needell , E. Rebrova , A. Zare

The coefficient of determination, known as $R^2$, is commonly used as a goodness-of-fit criterion for fitting linear models. $R^2$ is somewhat controversial when fitting nonlinear models, although it may be generalised on a case-by-case…

Methodology · Statistics 2021-12-23 Mark Levene , Aleksejus Kononovicius

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 robustness of risk measures to changes in underlying loss distributions (distributional uncertainty) is of crucial importance in making well-informed decisions. In this paper, we quantify, for the class of distortion risk measures with…

Risk Management · Quantitative Finance 2023-03-14 Carole Bernard , Silvana M. Pesenti , Steven Vanduffel

Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering. Although a greatly distorted metric space has a high degree of freedom to fit training data, it is prone to overfitting and…

Machine Learning · Computer Science 2015-05-12 Renjie Liao , Jianping Shi , Ziyang Ma , Jun Zhu , Jiaya Jia

Johnson-Lindenstrauss (JL) matrices implemented by sparse random synaptic connections are thought to be a prime candidate for how convergent pathways in the brain compress information. However, to date, there is no complete mathematical…

Neurons and Cognition · Quantitative Biology 2014-11-21 Zeyuan Allen-Zhu , Rati Gelashvili , Silvio Micali , Nir Shavit

Data subsampling is one of the most natural methods to approximate a massively large data set by a small representative proxy. In particular, sensitivity sampling received a lot of attention, which samples points proportional to an…

Data Structures and Algorithms · Computer Science 2024-06-04 Alexander Munteanu , Simon Omlor

Distortion is widely existed in the images captured by popular wide-angle cameras and fisheye cameras. Despite the long history of distortion rectification, accurately estimating the distortion parameters from a single distorted image is…

Computer Vision and Pattern Recognition · Computer Science 2024-04-30 Kang Liao , Chunyu Lin , Yao Zhao

Randomized dimensionality reduction is a widely-used algorithmic technique for speeding up large-scale Euclidean optimization problems. In this paper, we study dimension reduction for a variety of maximization problems, including…

Data Structures and Algorithms · Computer Science 2025-06-03 Jie Gao , Rajesh Jayaram , Benedikt Kolbe , Shay Sapir , Chris Schwiegelshohn , Sandeep Silwal , Erik Waingarten

Allen-Zhu, Gelashvili, Micali, and Shavit construct a sparse, sign-consistent Johnson-Lindenstrauss distribution, and prove that this distribution yields an essentially optimal dimension for the correct choice of sparsity. However, their…

Data Structures and Algorithms · Computer Science 2019-10-01 Meena Jagadeesan

In this work, we explore modewise Johnson-Lindenstrauss embeddings (JLEs) as a tool to reduce the computational cost and memory requirements of nuclear many-body methods. JLEs are randomized projections of high-dimensional data tensors onto…

Nuclear Theory · Physics 2023-05-04 A. Zare , R. Wirth , C. A. Haselby , H. Hergert , M. Iwen

We prove optimal sampling bounds achieving $(1\pm\varepsilon)$-relative error for a broad class of Lipschitz continuous classification loss functions under various regularization terms. This includes important functions such as logistic and…

Machine Learning · Computer Science 2026-05-25 Meysam Alishahi , Alexander Munteanu , Simon Omlor , Jeff M. Phillips

We introduce a new technique for reducing the dimension of the ambient space of low-degree polynomials in the Gaussian space while preserving their relative correlation structure, analogous to the Johnson-Lindenstrauss lemma. As…

Computational Complexity · Computer Science 2017-08-15 Badih Ghazi , Pritish Kamath , Prasad Raghavendra

Most of the existing methods for estimating the local intrinsic dimension of a data distribution do not scale well to high-dimensional data. Many of them rely on a non-parametric nearest neighbors approach which suffers from the curse of…

Minimizing a convex function of a measure with a sparsity-inducing penalty is a typical problem arising, e.g., in sparse spikes deconvolution or two-layer neural networks training. We show that this problem can be solved by discretizing the…

Optimization and Control · Mathematics 2020-11-04 Lenaic Chizat

We consider the problem of matching a metric space $(X,d_X)$ of size $k$ with a subspace of a metric space $(Y,d_Y)$ of size $n \geq k$, assuming that these two spaces have constant doubling dimension $\delta$. More precisely, given an…

Data Structures and Algorithms · Computer Science 2020-12-22 Corentin Allair , Antoine Vigneron

We propose the first general and practical framework to design certifiable algorithms for robust geometric perception in the presence of a large amount of outliers. We investigate the use of a truncated least squares (TLS) cost function,…

Optimization and Control · Mathematics 2020-10-20 Heng Yang , Luca Carlone