← Search

Alexander Semenenko

2 accepted papers

2026

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

ICLR 2026poster

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…

Cited by 0Source ↗code ↗Scholar ↗
2025

Efficient Distribution Matching of Representations via Noise-Injected Deep InfoMax

ICLR 2025poster

Deep InfoMax (DIM) is a well-established method for self-supervised representation learning (SSRL) based on maximization of the mutual information between the input and the output of a deep neural network encoder. Despite the DIM and contrastive SSRL in general being well-explored, the task of learn…

Cited by 0Source ↗PDF ↗Scholar ↗