skwdro: a library for Wasserstein distributionally robust machine learning

Дата публикации: 17-08-2026 20:26:00

We present skwdro, a Python library for training robust machine learning models.
The library is based on distributionally robust optimization using Wasserstein distances, popular in optimal transport and machine learnings. The goal of the library is to make the training of robust models easier for a wide audience by proposing a wrapper for PyTorch modules, enabling model loss' robustification with minimal code changes. It comes along with scikit-learn compatible estimators for some popular objectives. The core of the implementation relies on an entropic smoothing of the original robust objective, in order to ensure maximal model flexibility. The library is available at https://github.com/iutzeler/skwdro and the documentation at https://skwdro.readthedocs.io

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Global Fr{\'{e}}chet Manifold Learning for Random Objects, With Application to Low-Dimensional Wasserstein Representations of Distributional Data	0	5.55	17-08-2026
2	Doubly Debiased Robust Subsampling for Transfer Learning	0	8.06	17-08-2026
3	Graph-based Clustering Revisited: A Relaxation of Kernel k-Means Perspective	0	10.94	17-08-2026
4	End-to-End Deep Learning for Predicting Metric Space-Valued Outputs	0	10.66	17-08-2026
5	Kernel-based Distributed Learning	0	7	17-08-2026
6	Nonparametric generative modeling for time series via Schr{\"{o}}dinger bridge	0	5.53	17-08-2026
7	Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent	0	6.66	17-08-2026
8	Error Analysis for Deep ReLU Feedforward Density-Ratio Estimation with Bregman Divergence	0	8.78	17-08-2026
9	A Data-Augmented Contrastive Learning Approach to Nonparametric Density Estimation	0	8.4	17-08-2026
10	La distance de Wasserstein, une équation qui optimise le jardinage… et les modèles climatiques	0	6.84	26-05-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 4.74. Источник: jmlr.org.