English
Related papers

Related papers: Dimensionality Reduction has Quantifiable Imperfec…

200 papers

We prove an exponential size separation between depth 2 and depth 3 neural networks (with real inputs), when approximating a $\mathcal{O}(1)$-Lipschitz target function to constant accuracy, with respect to a distribution with support in the…

Machine Learning · Computer Science 2024-11-08 Itay Safran , Daniel Reichman , Paul Valiant

Solving large scale Optimal Transport (OT) in machine learning typically relies on sampling measures to obtain a tractable discrete problem. While the discrete solver's accuracy is controllable, the rate of convergence of the discretization…

Machine Learning · Statistics 2026-02-05 Ferdinand Genans , Olivier Wintenberger

Persistence diagrams, an important summary in topological data analysis, consist of a set of ordered pairs, each with positive multiplicity. Persistence diagrams are obtained via Mobius inversion and may be compared using a one-parameter…

Algebraic Topology · Mathematics 2025-02-19 Peter Bubenik , Alex Elchesen

In this work, we develop a new theory and method for sufficient dimension reduction (SDR) in single-index models, where SDR is a sub-field of supervised dimension reduction based on conditional independence. Our work is primarily motivated…

Machine Learning · Statistics 2024-05-31 Seungbeom Hong , Ilmun Kim , Jun Song

We investigate the Distributionally Robust Regret-Optimal (DR-RO) control of discrete-time linear dynamical systems with quadratic cost over an infinite horizon. Regret is the difference in cost obtained by a causal controller and a…

Systems and Control · Electrical Eng. & Systems 2024-01-01 Taylan Kargin , Joudi Hajar , Vikrant Malik , Babak Hassibi

Probability mass curves the data space with horizons. Let f be a multivariate probability density function with continuous second order partial derivatives. Consider the problem of estimating the true value of f(z) > 0 at a single point z,…

Data Analysis, Statistics and Probability · Physics 2009-11-06 Carlos C. Rodriguez

We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances between input and embedding samples are computed through a…

Machine Learning · Computer Science 2023-10-06 Hugues Van Assel , Cédric Vincent-Cuaz , Titouan Vayer , Rémi Flamary , Nicolas Courty

Searching for the $k$-nearest neighbors (KNN) in multimodal data retrieval is computationally expensive, particularly due to the inherent difficulty in comparing similarity measures across different modalities. Recent advances in multimodal…

Machine Learning · Computer Science 2025-08-25 Chengyu Gong , Gefei Shen , Luanzheng Guo , Nathan Tallent , Dongfang Zhao

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

Machine Learning · Statistics 2019-06-04 Giulia Luise , Alessandro Rudi , Massimiliano Pontil , Carlo Ciliberto

Dimensionality reduction (DR) techniques help analysts to understand patterns in high-dimensional spaces. These techniques, often represented by scatter plots, are employed in diverse science domains and facilitate similarity analysis among…

Machine Learning · Computer Science 2025-10-21 Wilson E. Marcílio-Jr , Danilo M. Eler , Fernando V. Paulovich , Rafael M. Martins

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

We provide an implementation to compute the flat metric in any dimension. The flat metric, also called dual bounded Lipschitz distance, generalizes the well-known Wasserstein distance $W_1$ to the case that the distributions are of unequal…

Machine Learning · Computer Science 2025-06-17 Henri Schmidt , Christian Düll

Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. The goal of this work is to quantify this scalability from three key aspects: (i)…

Machine Learning · Statistics 2022-10-18 Sloan Nietert , Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

We introduce LOT Wassmap, a computationally feasible algorithm to uncover low-dimensional structures in the Wasserstein space. The algorithm is motivated by the observation that many datasets are naturally interpreted as probability…

Machine Learning · Computer Science 2023-02-16 Alexander Cloninger , Keaton Hamm , Varun Khurana , Caroline Moosmüller

Whenever inspected by humans, reconstructed signals should not be distinguished from real ones. Typically, such a high perceptual quality comes at the price of high reconstruction error, and vice versa. We study this distortion-perception…

Information Theory · Computer Science 2024-02-06 Dror Freirich , Nir Weinberger , Ron Meir

Dimensionality reduction (DR) on the manifold includes effective methods which project the data from an implicit relational space onto a vectorial space. Regardless of the achievements in this area, these algorithms suffer from the lack of…

Machine Learning · Computer Science 2019-09-23 Babak Hosseini , Barbara Hammer

We introduce a novel and scalable Bayesian framework for multivariate-density-density regression (DDR), designed to model relationships between multivariate distributions. Our approach addresses the critical issue of distributions residing…

Methodology · Statistics 2025-09-24 Khai Nguyen , Yang Ni , Peter Mueller

We explore the infinite-horizon Distributionally Robust (DR) linear-quadratic control. While the probability distribution of disturbances is unknown and potentially correlated over time, it is confined within a Wasserstein-2 ball of a…

Optimization and Control · Mathematics 2024-08-13 Joudi Hajar , Taylan Kargin , Vikrant Malik , Babak Hassibi

We propose a fundamental metric for measuring the distance between two distributions. This metric, referred to as the decision-focused (DF) divergence, is tailored to stochastic linear optimization problems in which the objective…

Statistics Theory · Mathematics 2026-02-04 Suhan Liu , Mo Liu

Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient…

Optimization and Control · Mathematics 2026-04-09 Hong T. M. Chu