Research map / Probabilistic and scientific modeling / Variational and generative sampling
Functional data analysis for multivariate distributions through Wasserstein slicing
Han Chen, Hans-Georg Müller
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Maps samples of multivariate distributions into a Hilbert space via an invertible Wasserstein slicing transformation to enable functional data analysis of distributions.
Problem
Modeling samples of multivariate distributions is hard because distributions do not form a vector space, and prior transformation approaches to Hilbert spaces are mostly limited to the univariate case.
Approach
Uses a Wasserstein slicing method to transform multivariate distributions into a Hilbert space in an invertible way, so standard functional data analysis can be applied to samples of distributions.
Closest papers by meaning
- Gaussian Mixture Models in Hilbert Spaces via Kernel Methods (NeurIPS 2026 · similarity 0.83)
- Kernel Quantile Embeddings and Associated Probability Metrics (ICML 2025 · similarity 0.83)
- Sliced Wasserstein Estimation with Control Variates (ICLR 2024 · similarity 0.83)
- On Statistical Learning Theory for Distributional Inputs (ICML 2024 · similarity 0.83)
- Fourier Sliced-Wasserstein Embedding for Multisets and Measures (ICLR 2025 · similarity 0.83)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
