paper-with-me

Papers

Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence

2025-06-04 · Alexander Semenenko, Ivan Butakov, Alexey Frolov, Ivan Oseledets

Sliced Mutual Information (SMI) is widely used as a scalable alternative to mutual information for measuring non-linear statistical dependence. Despite its advantages, such as faster convergence, robustness to high dimensionality, and nullification only under statistical independence, we demonstrate that SMI is highly susceptible to data manipulation and exhibits counterintuitive behavior. Through extensive benchmarking and theoretical analysis, we show that SMI saturates easily, fails to detect increases in statistical dependence (even under linear transformations designed to enhance the extraction of information), prioritizes redundancy over informative content, and in some cases, performs worse than simpler dependence measures like the correlation coefficient.

📄 PDF Abstract BibTeX arXiv:2506.04053

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarking

Similar Papers 제목 키워드 기반

Slicing Mutual Information Generalization Bounds for Neural Networks

2024-06-06 · Kimia Nadjahi, Kristjan Greenewald, Rickard Brüel Gabrielsson, Justin Solomon

The ability of machine learning (ML) algorithms to generalize well to unseen data has been studied through the lens of information theory, by bounding the generalization error with the input-output mutual information (MI…

Generalization BoundsModel Compression

Sliced Wasserstein with Random-Path Projecting Directions

2024-01-29 · Khai Nguyen, Shujian Zhang, Tam Le, Nhat Ho

Slicing distribution selection has been used as an effective technique to improve the performance of parameter estimators based on minimizing sliced Wasserstein distance in applications. Previous works either utilize exp…

Denoising

Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution

2022-04-04 · Khai Nguyen, Nhat Ho

The conventional sliced Wasserstein is defined between two probability measures that have realizations as vectors. When comparing two probability measures over images, practitioners first need to vectorize images and the…

Slicing Unbalanced Optimal Transport

2023-06-12 · Clément Bonet, Kimia Nadjahi, Thibault Séjourné, Kilian Fatras 외

Optimal transport (OT) is a powerful framework to compare probability measures, a fundamental task in many statistical and machine learning problems. Substantial advances have been made in designing OT variants which are…

Computational EfficiencyGPU

Constrained Sliced Wasserstein Embedding

2025-06-02 · Navid Naderializadeh, Darian Salehi, Xinran Liu, Soheil Kolouri

Sliced Wasserstein (SW) distances offer an efficient method for comparing high-dimensional probability measures by projecting them onto multiple 1-dimensional probability distributions. However, identifying informative s…