ICML 2025poster0 citations

Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures

Jie Gao, Rajesh Jayaram, Benedikt Kolbe, Shay Sapir, Chris Schwiegelshohn, Sandeep Silwal, Erik Waingarten

Abstract

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 max-matching, max-spanning tree, as well as various measures for dataset diversity. For these problems, we show that the effect of dimension reduction is intimately tied to the *doubling dimension* $\lambda_X$ of the underlying dataset $X$---a quantity measuring intrinsic dimensionality of point sets. Specifically, the dimension required is $O(\lambda_X)$, which we also show is necessary for some of these problems. This is in contrast to classical dimension reduction results, whose dependence grow with the dataset size $|X|$. We also provide empirical results validating the quality of solutions found in the projected space, as well as speedups due to dimensionality reduction.

Dimensionality ReductionDimension ReductionGeometric OptimizationJohnson LindenstraussDiversity MaximizationDiversity
BibTeX
@inproceedings{
gao2025randomized,
title={Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures},
author={Jie Gao and Rajesh Jayaram and Benedikt Kolbe and Shay Sapir and Chris Schwiegelshohn and Sandeep Silwal and Erik Waingarten},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=Rcivp36KzO}
}
Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures · ICML 2025