paper-with-me

Papers

Using Low-Discrepancy Points for Data Compression in Machine Learning: An Experimental Comparison

2024-07-10 · Simone Göttlich, Jacob Heieck, Andreas Neuenkirch

Low-discrepancy points (also called Quasi-Monte Carlo points) are deterministically and cleverly chosen point sets in the unit cube, which provide an approximation of the uniform distribution. We explore two methods based on such low-discrepancy points to reduce large data sets in order to train neural networks. The first one is the method of Dick and Feischl [4], which relies on digital nets and an averaging procedure. Motivated by our experimental findings, we construct a second method, which again uses digital nets, but Voronoi clustering instead of averaging. Both methods are compared to the supercompress approach of [14], which is a variant of the K-means clustering algorithm. The comparison is done in terms of the compression error for different objective functions and the accuracy of the training of a neural network.

📄 PDF Abstract BibTeX arXiv:2407.07450

Code (0)

등록된 구현이 없습니다.

Tasks

ClusteringData Compression

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Similar Papers 제목 키워드 기반

Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks

2024-05-23 · T. Konstantin Rusch, Nathan Kirk, Michael M. Bronstein, Christiane Lemieux 외

Discrepancy is a well-known measure for the irregularity of the distribution of a point set. Point sets with small discrepancy are called low-discrepancy and are known to efficiently fill the space in a uniform manner. L…

Numerical Integration

Neural Low-Discrepancy Sequences

2025-10-04 · Michael Etienne Van Huffel, Nathan Kirk, Makram Chahine, Daniela Rus 외 arxiv

Low-discrepancy points are designed to efficiently fill the space in a uniform manner. This uniformity is highly advantageous in many problems in science and engineering, including in numerical integration, computer visi…

Abstract AlgebraMotion Planning

Distribution Compression in Near-linear Time

2021-11-15 · ICLR 2022 4 · Abhishek Shetty, Raaz Dwivedi, Lester Mackey

In distribution compression, one aims to accurately summarize a probability distribution $\mathbb{P}$ using a small number of representative points. Near-optimal thinning procedures achieve this goal by sampling $n$ poin…

On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning

2019-11-19 · Aritra Dutta, El Houcine Bergou, Ahmed M. Abdelmoniem, Chen-Yu Ho 외

Compressed communication, in the form of sparsification or quantization of stochastic gradients, is employed to reduce communication costs in distributed data-parallel training of deep neural networks. However, there exi…

Model CompressionQuantization

Debiased Distribution Compression

2024-04-18 · Lingxiao Li, Raaz Dwivedi, Lester Mackey

Modern compression methods can summarize a target distribution $\mathbb{P}$ more succinctly than i.i.d. sampling but require access to a low-bias input sequence like a Markov chain converging quickly to $\mathbb{P}$. We …