paper-with-me

Papers

Statistical and Topological Properties of Sliced Probability Divergences

2020-03-12 · NeurIPS 2020 12 · Kimia Nadjahi, Alain Durmus, Lénaïc Chizat, Soheil Kolouri, Shahin Shahrampour, Umut Şimşekli

The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and consists in computing the expected value of a `base divergence' between one-dimensional random projections of the two measures. However, the topological, statistical, and computational consequences of this technique have not yet been well-established. In this paper, we aim at bridging this gap and derive various theoretical properties of sliced probability divergences. First, we show that slicing preserves the metric axioms and the weak continuity of the divergence, implying that the sliced divergence will share similar topological properties. We then precise the results in the case where the base divergence belongs to the class of integral probability metrics. On the other hand, we establish that, under mild conditions, the sample complexity of a sliced divergence does not depend on the problem dimension. We finally apply our general results to several base divergences, and illustrate our theory on both synthetic and real data experiments.

📄 PDF Abstract BibTeX arXiv:2003.05783

Code (1)

kimiandj/sliced_div 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Statistical and Topological Properties of Gaussian Smoothed Sliced Probability Divergences

2021-10-20 · Alain Rakotomamonjy, Mokhtar Z. Alaya, Maxime Berar, Gilles Gasso

Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown, in applications such as domain adaptation, to p…

Domain AdaptationPrivacy Preserving

Gaussian-Smoothed Sliced Probability Divergences

2024-04-04 · Mokhtar Z. Alaya, Alain Rakotomamonjy, Maxime Berar, Gilles Gasso

Gaussian smoothed sliced Wasserstein distance has been recently introduced for comparing probability distributions, while preserving privacy on the data. It has been shown that it provides performances similar to its non…

Domain AdaptationPrivacy Preserving

Energy-Based Sliced Wasserstein Distance

2023-04-26 · NeurIPS 2023 11 · Khai Nguyen, Nhat Ho

The sliced Wasserstein (SW) distance has been widely recognized as a statistically effective and computationally efficient metric between two probability measures. A key component of the SW distance is the slicing distri…

Point cloud reconstruction

$(f,Γ)$-Divergences: Interpolating between $f$-Divergences and Integral Probability Metrics

2020-11-11 · Jeremiah Birrell, Paul Dupuis, Markos A. Katsoulakis, Yannis Pantazis 외

We develop a rigorous and general framework for constructing information-theoretic divergences that subsume both $f$-divergences and integral probability metrics (IPMs), such as the $1$-Wasserstein distance. We prove und…

Image GenerationUncertainty Quantification

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

2023-01-10 · NeurIPS 2023 11 · Khai Nguyen, Tongzheng Ren, Nhat Ho

Sliced Wasserstein (SW) distance suffers from redundant projections due to independent uniform random projecting directions. To partially overcome the issue, max K sliced Wasserstein (Max-K-SW) distance ($K\geq 1$), seek…