SPN Publications

    2017

  • Online Structure Learning for Sum-Product Networks with Gaussian Leaves. [pdf]
    Wilson Hsu, Agastya Kalra, and Pascal Poupart.
    International Conference on Learning Representations 5 (ICLR 2017) Workshop Track.
  • Compositional Kernel Machines. [pdf]
    Robert Gens and Pedro Domingos.
    International Conference on Learning Representations 5 (ICLR 2017) Workshop Track.
  • Poisson Sum-Product Networks: A Deep Architecture for Tractable Multivariate Poisson Distributions. [pdf]
    Alejandro Molina, Sriraam Natarajan, and Kristian Kersting.
    AAAI Conference on Artificial Intelligence 31 (AAAI 2017).
  • 2016

  • The Sum-Product Theorem: A Foundation for Learning Tractable Models. [pdf] [supplement]
    Abram Friesen and Pedro Domingos.
    International Conference on Machine Learning 33 (ICML 2016).
  • Collapsed Variational Inference for Sum-Product Networks. [pdf]
    Han Zhao, Tameem Adel, Geoff Gordon, and Brandon Amos.
    International Conference on Machine Learning 33 (ICML 2016).
  • Discriminative Structure Learning of Arithmetic Circuits. [pdf]
    Amirmohammad Rooshenas and Daniel Lowd.
    International Conference on Artificial Intelligence and Statistics 19 (AISTATS 2016).
  • Merging Strategies for Sum-Product Networks: From Trees to Graphs. [pdf]
    Tahrima Rahman and Vibhav Gogate.
    Uncertainty in Artificial Intelligence 32 (UAI 2016).
  • Learning Tractable Probabilistic Models for Fault Localization. [pdf]
    Aniruddh Nath and Pedro Domingos.
    AAAI Conference on Artificial Intelligence 30 (AAAI 2016).
  • A Unified Approach for Learning the Parameters of Sum-Product Networks. [pdf]
    Han Zhao, Pascal Poupart, and Geoff Gordon.
    Advances in Neural Information Processing Systems 29 (NIPS 2016).
  • 2015

  • Sum Product Networks for Activity Recognition.
    Mohamed Amer and Sinisa Todorovic.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2015).
  • Simplifying, Regularizing and Strengthening Sum-Product Network Structure Learning.
    Antonio Vergari and Nicola Di Mauro and Floriana Esposito.
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD 2015).
  • Recursive Decomposition for Nonconvex Optimization. [pdf] [supplement] [code]
    Abram L. Friesen and Pedro Domingos.
    International Joint Conference on Artificial Intelligence 24 (IJCAI 2015).
    Distinguished Paper Award
  • Learning and Inference in Tractable Probabilistic Knowledge Bases. [pdf]
    Mathias Niepert and Pedro Domingos.
    Uncertainty in Artificial Intelligence 31 (UAI 2015).
  • Learning the Structure of Sum-Product Networks via an SVD-based Algorithm.
    Tameem Adel, David Balduzzi, and Ali Ghodsi.
    Uncertainty in Artificial Intelligence 31 (UAI 2015).
  • On the Relationship between Sum-Product Networks and Bayesian Networks. [pdf]
    Han Zhao, Mazen Melibari, and Pascal Poupart.
    International Conference on Machine Learning 32 (ICML 2015).
  • On Theoretical Properties of Sum-Product Networks. [pdf]
    Robert Peharz, Sebastian Tschiatschek, Franz Pernkopf, and Pedro Domingos.
    International Conference on Artificial Intelligence and Statistics 18 (AISTATS 2015).
  • Learning Relational Sum-Product Networks. [pdf]
    Aniruddh Nath and Pedro Domingos.
    AAAI Conference on Artificial Intelligence 29 (AAAI 2015).
  • 2014

  • Language Modeling with Sum-Product Networks. [pdf] [code]
    Wei-Chen Cheng, Stanley Kok, Hoai Vu Pham, Hai Leong Chieu, and Kian Ming A. Chai.
    Annual Conference of the International Speech Communication Association 15 (INTERSPEECH 2014).
  • Non-Parametric Bayesian Sum-Product Networks. [pdf]
    Sang-Woo Lee, Christopher Watkins, and Byoung-Tak Zhang.
    Workshop on Learning Tractable Probabilistic Models (LTPM 2014).
  • Learning Tractable Statistical Relational Models. [pdf]
    Aniruddh Nath and Pedro Domingos.
    Workshop on Learning Tractable Probabilistic Models (LTPM 2014).
  • Learning Selective Sum-Product Networks. [pdf]
    Robert Peharz, Robert Gens, and Pedro Domingos.
    Workshop on Learning Tractable Probabilistic Models (LTPM 2014).
  • Sum-Product Networks for Structured Prediction: Context-Specific Deep Conditional Random Fields. [pdf]
    Martin Ratajczak, Sebastian Tschiatschek, and Franz Pernkopf.
    Workshop on Learning Tractable Probabilistic Models (LTPM 2014).
  • Modeling Speech with Sum-Product Networks: Application to Bandwidth Extension. [pdf]
    Robert Peharz, Georg Kapeller, Pejman Mowlaee, and Franz Pernkopf.
    IEEE International Conference on Acoustics, Speech, and Signal Processing 39 (ICASSP 2014).
  • Learning Sum-Product Networks with Direct and Indirect Interactions. [pdf]
    Amirmohammad Rooshenas and Daniel Lowd.
    International Conference on Machine Learning 31 (ICML 2014).
  • 2013

  • Greedy Part-Wise Learning of Sum-Product Networks. [pdf]
    Robert Peharz, Bernhard Geiger, and Franz Pernkopf.
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD 2013).
  • A Provably Efficient Algorithm for Training Deep Networks. [pdf]
    Roi Livni, Shai Shalev-Shwartz, and Ohad Shamir.
    arXiv, April 2013.
  • Learning the Structure of Sum-Product Networks. [pdf] [slides] [code and supplemental results]
    Robert Gens and Pedro Domingos.
    International Conference on Machine Learning 30 (ICML 2013).
  • 2012

  • Discriminative Learning of Sum-Product Networks. [pdf] [slides] [bib] [Talk Video]
    Robert Gens and Pedro Domingos.
    Advances in Neural Information Processing Systems 25 (NIPS 2012).
    Outstanding Student Paper Award
  • Learning the Architecture of Sum-Product Networks Using Clustering on Variables. [pdf]
    Aaron Dennis and Dan Ventura.
    Advances in Neural Information Processing Systems 25 (NIPS 2012).
  • Sum-product Networks for Modeling Activities with Stochastic Structure.
    Mohamed Amer and Sinisa Todorovic.
    Computer Vision and Pattern Recognition (CVPR 2012).
  • A Dynamic Programming Algorithm for Inference in Recursive Probabilistic Programs. [pdf]
    Andreas Stuhlm├╝ller and Noah D. Goodman.
    International Workshop on Statistical Relational AI 2 (StaRAI 2012).
  • 2011

  • Shallow vs. Deep Sum-Product Networks. [pdf]
    Olivier Delalleau and Yoshua Bengio.
    Advances in Neural Information Processing Systems 24 (NIPS 2011).
  • Sum-Product Networks: A New Deep Architecture. [pdf] [slides] [code and results]
    Hoifung Poon and Pedro Domingos.
    Uncertainty in Artificial Intelligence 27 (UAI 2011).
    Best Paper Award