Variational auto-encoders with Student's t-prior
Not on the map. Why?
Abstract (arXiv)
We propose a new structure for the variational auto-encoders (VAEs) prior, with the weakly informative multivariate Student's t-distribution. In the proposed model all distribution parameters are trained, thereby allowing for a more robust approximation of the underlying data distribution. We used Fashion-MNIST data in two experiments to compare the proposed VAEs with the standard Gaussian priors. Both experiments showed a better reconstruction of the images with VAEs using Student's t-prior distribution.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 1; 2025: 3; 2026: 2.
9 papers.
- 2023t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergencecited by 17
- 2024Flexible Tails for Normalizing Flowscited by 11
- 2022Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flowscited by 10
- 2021Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applicationscited by 9
- 2025ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Promptscited by 3
- 2026Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalancecited by 3
- 2026ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generationcited by 3
- 2025Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shiftscited by 1
- 2025Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modelingcited by 1
- 2026ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generation11 Aug 2026
- 2026Multimodal Deep Generative Model for Semi-Supervised Learning under Class Imbalance7 May 2026
- 2025Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling2 Sep 2025
- 2025ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Prompts27 Jun 2025
- 2025Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shifts20 Feb 2025
- 2024Flexible Tails for Normalizing Flows22 Jun 2024
- 2023t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence2 Dec 2023
- 2022Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flows16 May 2022
- 2021Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications25 Jul 2021