English
Related papers

Related papers: Worst-Case Risk Quantification under Distributiona…

200 papers

In safety-critical applications, machine learning models should generalize well under worst-case distribution shifts, that is, have a small robust risk. Invariance-based algorithms can provably take advantage of structural assumptions on…

Machine Learning · Statistics 2025-02-06 Julia Kostin , Nicola Gnecco , Fanny Yang

Depth measures are powerful tools for defining level sets in emerging, non--standard, and complex random objects such as high-dimensional multivariate data, functional data, and random graphs. Despite their favorable theoretical properties,…

Given additional distributional information in the form of moment restrictions, kernel density and distribution function estimators with implied generalised empirical likelihood probabilities as weights achieve a reduction in variance due…

Methodology · Statistics 2019-10-08 Vitaliy Oryshchenko , Richard J. Smith

In this paper, an optimization problem with uncertain constraint coefficients is considered. Possibility theory is used to model the uncertainty. Namely, a joint possibility distribution in constraint coefficient realizations, called…

Optimization and Control · Mathematics 2023-09-07 Romain Guillaume , Adam Kasperski , Pawel Zielinski

A rich line of recent work has studied distributionally robust learning approaches that seek to learn a hypothesis that performs well, in the worst-case, on many different distributions over a population. We argue that although the most…

Machine Learning · Computer Science 2024-05-10 Jabari Hastings , Christopher Jung , Charlotte Peale , Vasilis Syrgkanis

In a first part, we present a mathematical analysis of a general methodology of a probabilistic learning inference that allows for estimating a posterior probability model for a stochastic boundary value problem from a prior probability…

Machine Learning · Statistics 2022-06-08 Christian Soize

Embedding probability distributions into reproducing kernel Hilbert spaces (RKHS) has enabled powerful nonparametric methods such as the maximum mean discrepancy (MMD), a statistical distance with strong theoretical and computational…

Machine Learning · Statistics 2025-05-28 Masha Naslidnyk , Siu Lun Chau , François-Xavier Briol , Krikamol Muandet

This paper concerns quantitative analysis of errors generated by incompletely known data in convex minimization problems. The problems are discussed in the mixed setting and the duality gap is used as the fundamental error measure. The…

Numerical Analysis · Mathematics 2015-06-17 Olli Mali

We consider decision-making problems involving the optimization of linear objective functions with uncertain coefficients. The probability distribution of the coefficients--which are assumed to be stochastic in nature--is unknown to the…

Optimization and Control · Mathematics 2024-12-23 Eilyan Bitar

Accurate quantification of uncertainty is crucial for real-world applications of machine learning. However, modern deep neural networks still produce unreliable predictive uncertainty, often yielding over-confident predictions. In this…

Machine Learning · Computer Science 2020-10-29 Peng Cui , Wenbo Hu , Jun Zhu

In spatial statistics and machine learning, the kernel matrix plays a pivotal role in prediction, classification, and maximum likelihood estimation. A thorough examination reveals that for large sample sizes, the kernel matrix becomes…

Machine Learning · Statistics 2023-11-07 Hao Zhang

We propose a novel calibration method for computer simulators, dealing with the problem of covariate shift. Covariate shift is the situation where input distributions for training and test are different, and ubiquitous in applications of…

Machine Learning · Statistics 2020-03-20 Keiichi Kisamori , Motonobu Kanagawa , Keisuke Yamazaki

Kernel methods are a cornerstone of classical machine learning. The idea of using quantum computers to compute kernels has recently attracted attention. Quantum embedding kernels (QEKs) constructed by embedding data into the Hilbert space…

Kernel mean embeddings -- integrals of a kernel with respect to a probability distribution -- are essential in Bayesian quadrature, but also widely used in other computational tools for numerical integration or for statistical inference…

Machine Learning · Statistics 2025-04-29 François-Xavier Briol , Alexandra Gessner , Toni Karvonen , Maren Mahsereci

Comparing conditional distributions is a fundamental challenge in statistics and machine learning, with applications across a wide range of domains. While proposed methods for measuring discrepancies using kernel embeddings of distributions…

Machine Learning · Statistics 2026-05-05 Peter Moskvichev , Siu Lun Chau , Dino Sejdinovic

This paper studies the probabilistic function approximation problem over reproducing kernel Hilbert spaces. We show the existence and uniqueness of the optimizer under mild assumptions. Furthermore, we generalize the celebrated representer…

Functional Analysis · Mathematics 2025-07-16 Dongwei Chen , Kai-Hsiang Wang

In this paper, we address the risk estimation problem where one aims at estimating the probability of violation of safety constraints for a robot in the presence of bounded uncertainties with arbitrary probability distributions. In this…

Optimization and Control · Mathematics 2018-10-04 Ashkan Jasour , Andreas Hofmann , Brian C. Williams

Kernel conditional mean embeddings (CMEs) offer a powerful framework for representing conditional distribution, but they often face scalability and expressiveness challenges. In this work, we propose a new method that effectively combines…

Machine Learning · Statistics 2024-03-19 Eiki Shimizu , Kenji Fukumizu , Dino Sejdinovic

Empirical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distributions. Although numerous kernels between distributions have…

Machine Learning · Computer Science 2024-12-02 Oleksii Kachaiev , Stefano Recanatesi

A wide array of machine learning problems are formulated as the minimization of the expectation of a convex loss function on some parameter space. Since the probability distribution of the data of interest is usually unknown, it is is often…

Optimization and Control · Mathematics 2019-05-27 Emilie Chouzenoux , Henri Gérard , Jean-Christophe Pesquet