paper-with-me

Papers

Exact Statistical Inference for the Wasserstein Distance by Selective Inference

2021-09-29 · Vo Nguyen Le Duy, Ichiro Takeuchi

In this paper, we study statistical inference for the Wasserstein distance, which has attracted much attention and has been applied to various machine learning tasks. Several studies have been proposed in the literature, but almost all of them are based on asymptotic approximation and do not have finite-sample validity. In this study, we propose an exact (non-asymptotic) inference method for the Wasserstein distance inspired by the concept of conditional Selective Inference (SI). To our knowledge, this is the first method that can provide a valid confidence interval (CI) for the Wasserstein distance with finite-sample coverage guarantee, which can be applied not only to one-dimensional problems but also to multi-dimensional problems. We evaluate the performance of the proposed method on both synthetic and real-world datasets.

📄 PDF Abstract BibTeX arXiv:2109.14206

Code (0)

등록된 구현이 없습니다.

Tasks

valid

Similar Papers 제목 키워드 기반

Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation

2026-05-19 · Peter Matthew Jacobs, Jeff M. Phillips arxiv

Squared Wasserstein distance is a frequently used tool to measure discrepancy between probability distributions. This distance is typically computed between empirical measures of size $n$ from two underlying random sampl…

On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification

2020-06-22 · Tianyi Lin, Zeyu Zheng, Elynn Y. Chen, Marco Cuturi 외

Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators…

Learning with a Wasserstein Loss

2015-06-17 · NeurIPS 2015 12 · Charlie Frogner, Chiyuan Zhang, Hossein Mobahi, Mauricio Araya-Polo 외

Learning to predict multi-label outputs is challenging, but in many problems there is a natural metric on the outputs that can be used to improve predictions. In this paper we develop a loss function for multi-label lear…

Multi-Label LearningTAG

Estimation and inference for the Wasserstein distance between mixing measures in topic models

2022-06-26 · Xin Bing, Florentina Bunea, Jonathan Niles-Weed

The Wasserstein distance between mixing measures has come to occupy a central place in the statistical analysis of mixture models. This work proposes a new canonical interpretation of this distance and provides tools to …

Topic Modelsvalid

A Two-Step Computation of the Exact GAN Wasserstein Distance

2018-07-01 · ICML 2018 7 · Huidong Liu, Xianfeng GU, Dimitris Samaras

In this paper, we propose a two-step method to compute the Wasserstein distance in Wasserstein Generative Adversarial Networks (WGANs): 1) The convex part of our objective can be solved by linear programming; 2) The…

Vocal Bursts Valence Prediction