23.10.2026 16:59

Approximating f-Divergences with Rank Statistics

Spain IMDEA Software Institute Unknown author

IMDEA Software Institute zve 17. listopadu 2026 na přednášku Josého Manuela de Frutose Porase o aproximaci f-divergencí pomocí pořadových statistik. Přednáška představí teoretické vlastnosti metody i její využití včetně experimentů.

Tuesday, November 17, 2026

11:00 302-Mountain View and Zoom3 (https://zoom.us/j/3911012202, password:@s3)

José Manuel de Frutos Porras, PhD Student, Universidad Carlos III de Madrid (UC3M)

Approximating f-Divergences with Rank Statistics

Abstract:

Quantifying discrepancies between probability distributions is a fundamental problem in statistics and machine learning, with applications to hypothesis testing, divergence estimation, and generative modeling.

In this talk, we introduce a framework for approximating f-divergences using rank statistics, without requiring density estimation or density-ratio estimation. Our approach relies on rank histograms that capture discrepancies between distributions, leading to simple, bounded, and statistically consistent estimators.

We discuss the theoretical properties of these approximations, including their lower-bound interpretation and convergence guarantees. We also extend the framework to high-dimensional settings through random projections, yielding sliced f-divergence estimators.

Finally, we present numerical experiments illustrating the effectiveness of the proposed methods for divergence estimation and training implicit generative models.

Based on: Approximating f-Divergences with Rank Statistics, Viktor Stein and José Manuel de Frutos (ICML 2026).



https://software.imdea.org/events/invited-talks/2026/11-17
Author
Company / Organization
IMDEA Software Institute
Download
Share