English
Related papers

Related papers: Johnson-Lindenstrauss Compression with Neuroscienc…

200 papers

The problem of identifying sparse solutions for the link structure and dynamics of an unknown linear, time-invariant network is posed as finding sparse solutions x to Ax=b. If the sensing matrix A satisfies a rank condition, this problem…

Dynamical Systems · Mathematics 2014-11-18 David Hayden , Young Hwan Chang , Jorge Goncalves , Claire Tomlin

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

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

Machine Learning · Computer Science 2021-10-11 Elvis Nunez , Maxwell Horton , Anish Prabhu , Anurag Ranjan , Ali Farhadi , Mohammad Rastegari

For a set $X$ of $N$ points in $\mathbb{R}^D$, the Johnson-Lindenstrauss lemma provides random linear maps that approximately preserve all pairwise distances in $X$ -- up to multiplicative error $(1\pm \epsilon)$ with high probability --…

Probability · Mathematics 2023-07-18 Michael P. Casey

Optimizing the acquisition matrix is useful for compressed sensing of signals that are sparse in overcomplete dictionaries, because the acquisition matrix can be adapted to the particular correlations of the dictionary atoms. In this paper…

Information Theory · Computer Science 2013-09-17 Nicolae Cleju

Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge…

Machine Learning · Computer Science 2026-02-27 Changhai Zhou , Qian Qiao , Yuhua Zhou , Yuxin Wu , Shichao Weng , Weizhong Zhang , Cheng Jin

This paper analyzes circulant Johnson-Lindenstrauss (JL) embeddings which, as an important class of structured random JL embeddings, are formed by randomizing the column signs of a circulant matrix generated by a random vector. With the…

Information Theory · Computer Science 2013-08-30 Hui Zhang , Lizhi Cheng

Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously…

Computer Vision and Pattern Recognition · Computer Science 2018-04-20 Bin Dai , Chen Zhu , David Wipf

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

Dimension reduction is a key algorithmic tool with many applications including nearest-neighbor search, compressed sensing and linear algebra in the streaming model. In this work we obtain a {\em sparse} version of the fundamental tool in…

Data Structures and Algorithms · Computer Science 2015-03-14 Anirban Dasgupta , Ravi Kumar , Tamás Sarlós

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are…

Machine Learning · Computer Science 2023-06-06 Wes Gurnee , Neel Nanda , Matthew Pauly , Katherine Harvey , Dmitrii Troitskii , Dimitris Bertsimas

For any $n>1$ and $0<\varepsilon<1/2$, we show the existence of an $n^{O(1)}$-point subset $X$ of $\mathbb{R}^n$ such that any linear map from $(X,\ell_2)$ to $\ell_2^m$ with distortion at most $1+\varepsilon$ must have $m = \Omega(\min\{n,…

Information Theory · Computer Science 2014-11-11 Kasper Green Larsen , Jelani Nelson

We introduce an extension to the CLRS algorithmic learning benchmark, prioritizing scalability and the utilization of sparse representations. Many algorithms in CLRS require global memory or information exchange, mirrored in its execution…

Machine Learning · Computer Science 2023-11-21 Julian Minder , Florian Grötschla , Joël Mathys , Roger Wattenhofer

Efficient algorithms for the sparse solution of under-determined linear systems $Ax = b$ are known for matrices $A$ satisfying suitable assumptions like the restricted isometry property (RIP). Without such assumptions little is known and…

Machine Learning · Computer Science 2021-01-22 G. Welper

Recently, tensor data (or multidimensional array) have been generated in many modern applications, such as functional magnetic resonance imaging (fMRI) in neuroscience and videos in video analysis. Many efforts are made in recent years to…

Machine Learning · Computer Science 2023-08-10 Jiaqi Zhang , Yinghao Cai , Zhaoyang Wang , Beilun Wang

The Johnson-Lindenstrauss (JL) lemma is a cornerstone of dimensionality reduction in Euclidean space, but its applicability to non-Euclidean data has remained limited. This paper extends the JL lemma beyond Euclidean geometry to handle…

Data Structures and Algorithms · Computer Science 2025-10-28 Chengyuan Deng , Jie Gao , Kevin Lu , Feng Luo , Cheng Xin

We introduce sparse random projection, an important dimension-reduction tool from machine learning, for the estimation of discrete-choice models with high-dimensional choice sets. Initially, high-dimensional data are compressed into a…

Machine Learning · Statistics 2016-04-21 Khai X. Chiong , Matthew Shum

How does the geometric representation of a dataset change after the application of each randomly initialized layer of a neural network? The celebrated Johnson--Lindenstrauss lemma answers this question for linear fully-connected neural…

Machine Learning · Computer Science 2022-03-08 Ido Nachum , Jan Hązła , Michael Gastpar , Anatoly Khina

Our work is focused on the joint sparsity recovery problem where the common sparsity pattern is corrupted by Poisson noise. We formulate the confidence-constrained optimization problem in both least squares (LS) and maximum likelihood (ML)…

Machine Learning · Statistics 2013-10-10 E. Chunikhina , R. Raich , T. Nguyen

This work constructs Jonson-Lindenstrauss embeddings with best accuracy, as measured by variance, mean-squared error and exponential concentration of the length distortion. Lower bounds for any data and embedding dimensions are determined,…

Machine Learning · Computer Science 2021-01-05 Maciej Skorski