English
Related papers

Related papers: Bures-Wasserstein Importance-Weighted Evidence Low…

200 papers

In the past decade gradient-based deep learning has revolutionized several applications. However, this rapid advancement has highlighted the need for a deeper theoretical understanding of its limitations. Research has shown that, in many…

Machine Learning · Computer Science 2025-05-30 Rustem Takhanov

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 study first-order optimality conditions for constrained optimization in the Wasserstein space, whereby one seeks to minimize a real-valued function over the space of probability measures endowed with the Wasserstein distance. Our…

Optimization and Control · Mathematics 2025-03-03 Nicolas Lanzetti , Saverio Bolognani , Florian Dörfler

The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the posterior and prior. In NLP, VAEs are extremely difficult to…

Computation and Language · Computer Science 2019-04-15 Hareesh Bahuleyan , Lili Mou , Hao Zhou , Olga Vechtomova

In this work, we study the weighted empirical risk minimization (weighted ERM) schema, in which an additional data-dependent weight function is incorporated when the empirical risk function is being minimized. We show that under a general…

Machine Learning · Computer Science 2025-01-07 Yikai Zhang , Jiahe Lin , Fengpei Li , Songzhu Zheng , Anant Raj , Anderson Schneider , Yuriy Nevmyvaka

Searching for gravitational-wave signals is a challenging and computationally intensive endeavor undertaken by multiple independent analysis pipelines. While detection depends only on observed noisy data, it is sometimes inconsistently…

General Relativity and Quantum Cosmology · Physics 2024-03-15 Matthew Mould , Christopher J. Moore , Davide Gerosa

We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in computing the Wasserstein barycenter of $m$ discrete probability measures supported on a finite metric space of size $n$. We show first that the…

Computational Complexity · Computer Science 2022-06-07 Tianyi Lin , Nhat Ho , Xi Chen , Marco Cuturi , Michael I. Jordan

Transfer learning is a popular strategy to leverage external knowledge and improve statistical efficiency, particularly with a limited target sample. We propose a novel knowledge-guided Wasserstein Distributionally Robust Optimization…

Machine Learning · Computer Science 2025-02-13 Zitao Wang , Ziyuan Wang , Molei Liu , Nian Si

Bayesian optimisation (BO) is a standard approach for sample-efficient global optimisation of expensive black-box functions, yet its scalability to high dimensions remains challenging. Here, we investigate nonlinear dimensionality reduction…

Optimization and Control · Mathematics 2025-10-20 Luo Long , Coralia Cartis , Paz Fink Shustin

The smooth 1-Wasserstein distance (SWD) $W_1^\sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation while preserving the Wasserstein structure. Indeed, SWD exhibits parametric convergence…

Statistics Theory · Mathematics 2022-02-28 Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

Mixed-resolution architectures, combining high-resolution (analog) data with coarsely quantized (e.g., 1-bit) data, are widely employed in emerging communication and radar systems to reduce hardware costs and power consumption. However, the…

Signal Processing · Electrical Eng. & Systems 2025-08-29 Yaniv Mazor , Tirza Routtenberg

Training deep generative models like Variational Autoencoders (VAEs) requires propagating gradients through stochastic latent variables, which introduces estimation variance that can slow convergence and degrade performance. In this paper,…

Machine Learning · Computer Science 2026-02-27 Zilei Shao , Anji Liu , Guy Van den Broeck

Gaussian process (GP) regression is widely used for uncertainty quantification, yet the standard formulation assumes noise-free covariates. When inputs are measured with error, this errors-in-variables (EIV) setting can lead to…

Methodology · Statistics 2026-03-19 Hengrui Luo , Xiaoye S. Li , Yang Liu , Marcus Noack , Ji Qiang , Mark D. Risser

This paper studies the problem of distributed weighted least-squares (WLS) estimation for an interconnected linear measurement network with additive noise. Two types of measurements are considered: self measurements for individual nodes,…

Systems and Control · Electrical Eng. & Systems 2020-02-27 Qiqi Yang , Zhaorong Zhang , Minyue Fu

In this paper, we consider the problem of parametric empirical Bayes estimation of an i.i.d. prior in high-dimensional Bayesian linear regression, with random design. We obtain the asymptotic distribution of the variational Empirical Bayes…

Statistics Theory · Mathematics 2026-02-25 Seunghyun Lee , Nabarun Deb

Instrumental variables (IV) estimation is a fundamental method in econometrics and statistics for estimating causal effects in the presence of unobserved confounding. However, challenges such as untestable model assumptions and poor finite…

Econometrics · Economics 2024-12-24 Zhaonan Qu , Yongchan Kwon

In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the optimal transport and machine learning literature, due to…

Machine Learning · Statistics 2025-08-21 Christophe Vauthier , Anna Korba , Quentin Mérigot

We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we…

Machine Learning · Statistics 2021-04-23 Mokhtar Z. Alaya , Maxime Bérar , Gilles Gasso , Alain Rakotomamonjy

We introduce a fully stochastic gradient based approach to Bayesian optimal experimental design (BOED). Our approach utilizes variational lower bounds on the expected information gain (EIG) of an experiment that can be simultaneously…

Machine Learning · Statistics 2020-02-28 Adam Foster , Martin Jankowiak , Matthew O'Meara , Yee Whye Teh , Tom Rainforth

Optimal transport (OT) and the related Wasserstein metric (W) are powerful and ubiquitous tools for comparing distributions. However, computing pairwise Wasserstein distances rapidly becomes intractable as cohort size grows. An attractive…

Machine Learning · Computer Science 2024-06-05 Doron Haviv , Russell Zhang Kunes , Thomas Dougherty , Cassandra Burdziak , Tal Nawy , Anna Gilbert , Dana Pe'er