Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Robert Peharz

Robert Peharz

Graz University of Technology

Joints in Random Forests


Jul 11, 2020
Alvaro H. C. Correia, Robert Peharz, Cassio P. de Campos


  Access Paper or Ask Questions

Towards Robust Classification with Deep Generative Forests


Jul 11, 2020
Alvaro H. C. Correia, Robert Peharz, Cassio de Campos

* Presented at the ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning 

  Access Paper or Ask Questions

Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits


Apr 13, 2020
Robert Peharz, Steven Lang, Antonio Vergari, Karl Stelzner, Alejandro Molina, Martin Trapp, Guy Van den Broeck, Kristian Kersting, Zoubin Ghahramani


  Access Paper or Ask Questions

Resource-Efficient Neural Networks for Embedded Systems


Jan 07, 2020
Wolfgang Roth, Günther Schindler, Matthias Zöhrer, Lukas Pfeifenberger, Robert Peharz, Sebastian Tschiatschek, Holger Fröning, Franz Pernkopf, Zoubin Ghahramani

* arXiv admin note: text overlap with arXiv:1812.02240 

  Access Paper or Ask Questions

Sum-Product Network Decompilation


Dec 20, 2019
Cory J. Butz, Jhonatan S. Oliveira, Robert Peharz


  Access Paper or Ask Questions

Deep Structured Mixtures of Gaussian Processes


Oct 10, 2019
Martin Trapp, Robert Peharz, Franz Pernkopf, Carl E. Rasmussen


  Access Paper or Ask Questions

Optimisation of Overparametrized Sum-Product Networks


May 29, 2019
Martin Trapp, Robert Peharz, Franz Pernkopf

* Workshop on Tractable Probabilistic Models (TPM) at ICML 2019 

  Access Paper or Ask Questions

Bayesian Learning of Sum-Product Networks


May 26, 2019
Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani


  Access Paper or Ask Questions

Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures


May 21, 2019
Xiaoting Shao, Alejandro Molina, Antonio Vergari, Karl Stelzner, Robert Peharz, Thomas Liebig, Kristian Kersting

* 13 pages, 6 figures 

  Access Paper or Ask Questions

SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks


Jan 11, 2019
Alejandro Molina, Antonio Vergari, Karl Stelzner, Robert Peharz, Pranav Subramani, Nicola Di Mauro, Pascal Poupart, Kristian Kersting

* 4 pages, 1 figure, code 

  Access Paper or Ask Questions

Efficient and Robust Machine Learning for Real-World Systems


Dec 05, 2018
Franz Pernkopf, Wolfgang Roth, Matthias Zoehrer, Lukas Pfeifenberger, Guenther Schindler, Holger Froening, Sebastian Tschiatschek, Robert Peharz, Matthew Mattina, Zoubin Ghahramani


  Access Paper or Ask Questions

Automatic Bayesian Density Analysis


Oct 03, 2018
Antonio Vergari, Alejandro Molina, Robert Peharz, Zoubin Ghahramani, Kristian Kersting, Isabel Valera


  Access Paper or Ask Questions

Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters


Sep 30, 2018
Marton Havasi, Robert Peharz, José Miguel Hernández-Lobato

* Under review as a conference paper at ICLR 2019 

  Access Paper or Ask Questions

Learning Deep Mixtures of Gaussian Process Experts Using Sum-Product Networks


Sep 12, 2018
Martin Trapp, Robert Peharz, Carl E. Rasmussen, Franz Pernkopf

* Presented at the Workshop on Tractable Probabilistic Models (TPM 2018), ICML 2018 

  Access Paper or Ask Questions

Probabilistic Deep Learning using Random Sum-Product Networks


Jun 22, 2018
Robert Peharz, Antonio Vergari, Karl Stelzner, Alejandro Molina, Martin Trapp, Kristian Kersting, Zoubin Ghahramani


  Access Paper or Ask Questions

Safe Semi-Supervised Learning of Sum-Product Networks


Oct 10, 2017
Martin Trapp, Tamas Madl, Robert Peharz, Franz Pernkopf, Robert Trappl

* Conference on Uncertainty in Artificial Intelligence (UAI), 2017 

  Access Paper or Ask Questions

On the Latent Variable Interpretation in Sum-Product Networks


Oct 28, 2016
Robert Peharz, Robert Gens, Franz Pernkopf, Pedro Domingos

* Revised version, accepted for publication in IEEE Transactions on Machine Intelligence and Pattern Analysis (TPAMI). Shortened and revised Section 4: Thanks to our reviewers, pointing out that Theorem 2 holds for selective SPNs. Added paragraph in Section 2.1, relating sizes of original/augmented SPNs. Fixed typos, rephrased sentences, revised references 

  Access Paper or Ask Questions

Exact Maximum Margin Structure Learning of Bayesian Networks


Jun 27, 2012
Robert Peharz, Franz Pernkopf

* ICML 

  Access Paper or Ask Questions