On Relaxing Determinism in Arithmetic Circuits

The past decade has seen a significant interest in learning tractable probabilistic representations. Arithmetic circuits (ACs) were among the first proposed tractable representations, with some subsequent representations being instances of ACs with weaker or stronger properties. In this paper, we provide a formal basis under which variants on ACs can be compared, and where the precise roles and semantics of their various properties can be made more transparent. This allows us to place some recent developments on ACs in a clearer perspective and to also derive new results for ACs. This includes an exponential separation between ACs with and without determinism; completeness and incompleteness results; and tractability results (or lack thereof) when computing most probable explanations (MPEs).

[1]  Franz Pernkopf,et al.  On the Latent Variable Interpretation in Sum-Product Networks , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Adnan Darwiche,et al.  On the Robustness of Most Probable Explanations , 2006, UAI.

[3]  Cassio Polpo de Campos.  Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence New Complexity Results for MAP in Bayesian Networks , 2022 .

[4]  Pascal Poupart,et al.  A Unified Approach for Learning the Parameters of Sum-Product Networks , 2016, NIPS.

[5]  Adnan Darwiche,et al.  On the Tractable Counting of Theory Models and its Application to Truth Maintenance and Belief Revision , 2001, J. Appl. Non Class. Logics.

[6]  Solomon Eyal Shimony,et al.  Finding MAPs for Belief Networks is NP-Hard , 1994, Artif. Intell..

[7]  Adnan Darwiche,et al.  A differential approach to inference in Bayesian networks , 2000, JACM.

[8]  Adnan Darwiche,et al.  Decomposable negation normal form , 2001, JACM.

[9]  Pedro M. Domingos,et al.  Learning Selective Sum-Product Networks , 2014 .

[10]  Dan Ventura,et al.  Greedy Structure Search for Sum-Product Networks , 2015, IJCAI.

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

[12]  Adnan Darwiche,et al.  Tractable Operations for Arithmetic Circuits of Probabilistic Models , 2016, NIPS.

[13]  Luc De Raedt,et al.  Algebraic model counting , 2012, J. Appl. Log..

[14]  Daniel Lowd,et al.  Learning Sum-Product Networks with Direct and Indirect Variable Interactions , 2014, ICML.

[15]  Dan Roth,et al.  On the Hardness of Approximate Reasoning , 1993, IJCAI.

[16]  A. Darwiche,et al.  Complexity Results and Approximation Strategies for MAP Explanations , 2011, J. Artif. Intell. Res..

[17]  Adnan Darwiche,et al.  A Logical Approach to Factoring Belief Networks , 2002, KR.

[18]  Adnan Darwiche,et al.  On probabilistic inference by weighted model counting , 2008, Artif. Intell..

[19]  Pedro M. Domingos,et al.  The Sum-Product Theorem: A Foundation for Learning Tractable Models , 2016, ICML.

[20]  Pierre Marquis,et al.  A Knowledge Compilation Map , 2002, J. Artif. Intell. Res..

[21]  Adnan Darwiche,et al.  Modeling and Reasoning with Bayesian Networks , 2009 .

[22]  Friedrich Slivovsky,et al.  Knowledge Compilation Meets Communication Complexity , 2016, IJCAI.

[23]  Pedro M. Domingos,et al.  Sum-product networks: A new deep architecture , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[24]  Pedro M. Domingos,et al.  Learning Arithmetic Circuits , 2008, UAI.