论文信息 - Probability Distributions over Structured Spaces

Probability Distributions over Structured Spaces

Our goal is to develop general-purpose techniques for probabilistic reasoning and learning in structured spaces. These spaces are characterized by complex logical constraints on what constitutes a possible world. We propose a tractable formalism, called probabilistic sentential decision diagrams, and show it effectively learns structured probability distributions in two applications: product configuration and preference learning.

Guy Van den Broeck | Adnan Darwiche | Arthur Choi | Adnan Darwiche | Arthur Choi

[1] Craig Boutilier,et al. Learning Mallows Models with Pairwise Preferences , 2011, ICML.

[2] Matthew Richardson,et al. Markov logic networks , 2006, Machine Learning.

[3] Stuart J. Russell,et al. BLOG: Probabilistic Models with Unknown Objects , 2005, IJCAI.

[4] Rina Dechter,et al. Mixed deterministic and probabilistic networks , 2008, Annals of Mathematics and Artificial Intelligence.

[5] Vibhav Gogate,et al. SampleSearch: A Scheme that Searches for Consistent Samples , 2007, AISTATS.

[6] Andrew McCallum,et al. Introduction to Statistical Relational Learning , 2007 .

[7] C. L. Mallows. NON-NULL RANKING MODELS. I , 1957 .

[8] Kristian Kersting,et al. Lifted Probabilistic Inference , 2012, ECAI.

[9] Gökhan BakIr,et al. Predicting Structured Data , 2008 .

[10] Adnan Darwiche,et al. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence SDD: A New Canonical Representation of Propositional Knowledge Bases , 2022 .

[11] Pedro M. Domingos,et al. Sound and Efficient Inference with Probabilistic and Deterministic Dependencies , 2006, AAAI.

[12] Ming-Wei Chang,et al. Learning and Inference with Constraints , 2008, AAAI.

[13] Craig A. Knoblock,et al. PDDL-the planning domain definition language , 1998 .

[14] Guy Van den Broeck,et al. Probabilistic Sentential Decision Diagrams , 2014, KR.