Antonio Vergari

Alumni

Empirical Inference

Overview
Publications

My research here focuses on learning deep probabilistic models, exploiting them for exact and tractable inference, and ultimately aiming to automate machine learning, starting from density estimation for heterogeneous data. I am also interested in integrating symbolic and relational representations into statistical models.

6 results (View BibTeX file of all listed publications)

2020

From Variational to Deterministic Autoencoders

Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B.

8th International Conference on Learning Representations (ICLR) , April 2020, *equal contribution (conference)

Abstract

Variational Autoencoders (VAEs) provide a theoretically-backed framework for deep generative models. However, they often produce “blurry” images, which is linked to their training objective. Sampling in the most popular implementation, the Gaussian VAE, can be interpreted as simply injecting noise to the input of a deterministic decoder. In practice, this simply enforces a smooth latent space structure. We challenge the adoption of the full VAE framework on this specific point in favor of a simpler, deterministic one. Specifically, we investigate how substituting stochasticity with other explicit and implicit regularization schemes can lead to a meaningful latent space without having to force it to conform to an arbitrarily chosen prior. To retrieve a generative mechanism for sampling new data points, we propose to employ an efficient ex-post density estimation step that can be readily adopted both for the proposed deterministic autoencoders as well as to improve sample quality of existing VAEs. We show in a rigorous empirical study that regularized deterministic autoencoding achieves state-of-the-art sample quality on the common MNIST, CIFAR-10 and CelebA datasets.

ei ps

arXiv link (url) [BibTex]

2020

ei ps Ghosh*, P., Sajjadi*, M. S. M., Vergari, A., Black, M. J., Schölkopf, B. From Variational to Deterministic Autoencoders 8th International Conference on Learning Representations (ICLR) , April 2020, *equal contribution (conference)

arXiv link (url) [BibTex]

2019

Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning

Peharz, R., Vergari, A., Stelzner, K., Molina, A., Shao, X., Trapp, M., Kersting, K., Ghahramani, Z.

Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), pages: 124, (Editors: Amir Globerson and Ricardo Silva), AUAI Press, July 2019 (conference)

link (url) [BibTex]

2019

ei Peharz, R., Vergari, A., Stelzner, K., Molina, A., Shao, X., Trapp, M., Kersting, K., Ghahramani, Z. Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning Proceedings of the 35th Conference on Uncertainty in Artificial Intelligence (UAI), pages: 124, (Editors: Amir Globerson and Ricardo Silva), AUAI Press, July 2019 (conference)

link (url) [BibTex]

Automatic Bayesian Density Analysis

Vergari, A., Molina, A., Peharz, R., Ghahramani, Z., Kersting, K., Valera, I.

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-19), 33:01, pages: 5207-5215, AAAI.org, AAAI-19, January 2019 (conference)

arXiv DOI [BibTex]

ei Vergari, A., Molina, A., Peharz, R., Ghahramani, Z., Kersting, K., Valera, I. Automatic Bayesian Density Analysis Proceedings of the AAAI Conference on Artificial Intelligence (AAAI-19), 33:01, pages: 5207-5215, AAAI.org, AAAI-19, January 2019 (conference)

arXiv DOI [BibTex]

2018

Bayesian Nonparametric Hawkes Processes

Kapoor, J., Vergari, A., Gomez Rodriguez, M., Valera, I.

Bayesian Nonparametrics workshop at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

2018

ei Kapoor, J., Vergari, A., Gomez Rodriguez, M., Valera, I. Bayesian Nonparametric Hawkes Processes Bayesian Nonparametrics workshop at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

Probabilistic Deep Learning using Random Sum-Product Networks

Peharz, R., Vergari, A., Stelzner, K., Molina, A., Trapp, M., Kersting, K., Ghahramani, Z.

2018 (conference) Submitted

arXiv [BibTex]

ei Peharz, R., Vergari, A., Stelzner, K., Molina, A., Trapp, M., Kersting, K., Ghahramani, Z. Probabilistic Deep Learning using Random Sum-Product Networks 2018 (conference) Submitted

arXiv [BibTex]

Visualizing and understanding Sum-Product Networks

Vergari, A., Di Mauro, N., Esposito, F.

Machine Learning, 2018 (article)

DOI [BibTex]

ei Vergari, A., Di Mauro, N., Esposito, F. Visualizing and understanding Sum-Product Networks Machine Learning, 2018 (article)

DOI [BibTex]

Antonio Vergari

2020

From Variational to Deterministic Autoencoders

2020

2019

Random Sum-Product Networks: A Simple and Effective Approach to Probabilistic Deep Learning

2019

Automatic Bayesian Density Analysis

2018

Bayesian Nonparametric Hawkes Processes

2018

Probabilistic Deep Learning using Random Sum-Product Networks

Visualizing and understanding Sum-Product Networks

Latest News

Links

Contact Us