English
Related papers

Related papers: Dimensionality Reduction and Wasserstein Stability…

200 papers

Dimensionality reduction is a classical technique widely used for data analysis. One foundational instantiation is Principal Component Analysis (PCA), which minimizes the average reconstruction error. In this paper, we introduce the…

Discrete Mathematics · Computer Science 2020-06-17 Uthaipon Tantipongpipat , Samira Samadi , Mohit Singh , Jamie Morgenstern , Santosh Vempala

This paper presents a distance-based discriminative framework for learning with probability distributions. Instead of using kernel mean embeddings or generalized radial basis kernels, we introduce embeddings based on dissimilarity of…

Machine Learning · Computer Science 2018-11-16 Alain Rakotomamonjy , Abraham Traoré , Maxime Berar , Rémi Flamary , Nicolas Courty

Studying the stability of partially observed Markov decision processes (POMDPs) with respect to perturbations in either transition or observation kernels is a significant problem. While asymptotic robustness/stability results as approximate…

Optimization and Control · Mathematics 2025-09-15 Yunus Emre Demirci , Ali Devran Kara , Serdar Yüksel

Principal Components Regression (PCR) is a traditional tool for dimension reduction in linear regression that has been both criticized and defended. One concern about PCR is that obtaining the leading principal components tends to be…

Statistics Theory · Mathematics 2017-10-10 Martin Slawski

We consider the 2-Wasserstein space of probability measures supported on the unit-circle, and propose a framework for Principal Component Analysis (PCA) for data living in such a space. We build on a detailed investigation of the optimal…

Methodology · Statistics 2023-04-06 Mario Beraha , Matteo Pegoraro

Regression discontinuity and kink designs are typically analyzed through mean effects, even when treatment changes the shape of the entire outcome distribution. To address this, we introduce distributional discontinuity designs, a framework…

Methodology · Statistics 2026-02-24 Kyle Schindl , Larry Wasserman

We present the first minimax risk bounds for estimators of the spectral measure in multivariate linear factor models, where observations are linear combinations of regularly varying latent factors. Non-asymptotic convergence rates are…

Statistics Theory · Mathematics 2024-11-12 Xuhui Zhang , Jose Blanchet , Youssef Marzouk , Viet Anh Nguyen , Sven Wang

The study of stability and sensitivity of statistical methods or algorithms with respect to their data is an important problem in machine learning and statistics. The performance of the algorithm under resampling of the data is a…

Statistics Theory · Mathematics 2023-02-15 Haoyu Wang

We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport…

Optimization and Control · Mathematics 2025-03-27 Jie Wang , Rui Gao , Yao Xie

Kernel methods provide a principled approach to nonparametric learning. While their basic implementations scale poorly to large problems, recent advances showed that approximate solvers can efficiently handle massive datasets. A shortcoming…

Machine Learning · Computer Science 2022-01-19 Giacomo Meanti , Luigi Carratino , Ernesto De Vito , Lorenzo Rosasco

In the context of kernel methods, the similarity between data points is encoded by the kernel function which is often defined thanks to the Euclidean distance, a common example being the squared exponential kernel. Recently, other distances…

Machine Learning · Computer Science 2020-02-06 Henri De Plaen , Michaël Fanuel , Johan A. K. Suykens

Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances between probability distributions that have attracted abundant…

Machine Learning · Statistics 2023-06-01 Titouan Vayer , Rémi Gribonval

Modelling a large collection of functional time series arises in a broad spectral of real applications. Under such a scenario, not only the number of functional variables can be diverging with, or even larger than the number of temporally…

Statistics Theory · Mathematics 2021-09-01 Shaojun Guo , Xinghao Qiao

Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions. The recent developments on…

Machine Learning · Computer Science 2015-11-11 Soheil Kolouri , Yang Zou , Gustavo K. Rohde

We propose a robust inferential procedure for assessing uncertainties of parameter estimation in high-dimensional linear models, where the dimension $p$ can grow exponentially fast with the sample size $n$. Our method combines the…

Machine Learning · Statistics 2015-03-19 Tianqi Zhao , Mladen Kolar , Han Liu

The present paper provides a new representation of the solution to the fragmentation equation as a power series in the Banach space of Radon measures endowed with the total variation norm. This representation is used to justify how the…

Analysis of PDEs · Mathematics 2023-06-19 Marie Doumic , Miguel Escobedo , Magali Tournus

Principal component regression (PCR) is a popular technique for fixed-design error-in-variables regression, a generalization of the linear regression setting in which the observed covariates are corrupted with random noise. We provide the…

Machine Learning · Computer Science 2024-08-06 Anish Agarwal , Keegan Harris , Justin Whitehouse , Zhiwei Steven Wu

For a class of stochastic models with Gaussian and rough mean-reverting volatility that embeds the genuine rough Stein-Stein model, we study the weak approximation rate when using a Euler type scheme with integrated kernels. Our first…

Probability · Mathematics 2026-02-23 Aurélien Alfonsi , Ahmed Kebaier

We study the problem of estimating the effect function for a continuous treatment, which maps each treatment value to a population-averaged outcome. A central challenge in this setting is confounding: treatment assignment often depends on…

Methodology · Statistics 2026-05-29 Seok-Jin Kim , Kaizheng Wang

Nonlinear component analysis such as kernel Principle Component Analysis (KPCA) and kernel Canonical Correlation Analysis (KCCA) are widely used in machine learning, statistics and data analysis, but they can not scale up to big datasets.…

Machine Learning · Computer Science 2016-01-12 Bo Xie , Yingyu Liang , Le Song