cs.LGFeb 2, 2026

Deep Multivariate Models with Parametric Conditionals

Authors: Dmitrij Schlesinger, Boris Flach, Alexander Shekhovtsov

Organizations: Dresden University of Technology · Czech Technical University in Prague

Abstract

We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentations, image attributes, and latent variables. When developing such models, most existing works start from an application task and design the model components and their dependencies to meet the needs of the chosen task. This has the disadvantage of limiting the applicability of the resulting model for other downstream tasks. Here, instead, we propose to represent the joint probability distribution by means of conditional probability distributions for each group of variables conditioned on the rest. Such models can then be used for practically any possible downstream task. Their learning can be approached as training a parametrised Markov chain kernel by maximising the data likelihood of its limiting distribution. This has the additional advantage of allowing a wide range of semi-supervised learning scenarios.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Unpaired Joint Distribution Modeling via Multi-Scale Image Representations

    Jul 9, 2026Yihang Zou, Hui Zhang, Zuowei Shen +1Visual Representation LearningUnsupervised Representation Learning