Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.01953 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910008717869056 |
|---|---|
| author | Schlesinger, Dmitrij Flach, Boris Shekhovtsov, Alexander |
| author_facet | Schlesinger, Dmitrij Flach, Boris Shekhovtsov, Alexander |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01953 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deep Multivariate Models with Parametric Conditionals Schlesinger, Dmitrij Flach, Boris Shekhovtsov, Alexander Machine Learning 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. |
| title | Deep Multivariate Models with Parametric Conditionals |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.01953 |