Timezone: »
Circuit representations are becoming the lingua franca to express and reason about tractable generative and discriminative models. In this paper, we show how complex inference scenarios for these models that commonly arise in machine learning---from computing the expectations of decision tree ensembles to information-theoretic divergences of sum-product networks---can be represented in terms of tractable modular operations over circuits. Specifically, we characterize the tractability of simple transformations---sums, products, quotients, powers, logarithms, and exponentials---in terms of sufficient structural constraints of the circuits they operate on, and present novel hardness results for the cases in which these properties are not satisfied. Building on these operations, we derive a unified framework for reasoning about tractable models that generalizes several results in the literature and opens up novel tractable inference scenarios.
Author Information
Antonio Vergari (University of California, Los Angeles)
YooJung Choi (UCLA)
Anji Liu (University of California, Los Angeles)
Stefano Teso (University of Trento)
Guy Van den Broeck (UCLA)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Oral: A Compositional Atlas of Tractable Circuit Operations for Probabilistic Inference »
Wed. Dec 8th 04:40 -- 04:55 PM Room
More from the Same Authors
-
2021 Spotlight: Interactive Label Cleaning with Example-based Explanations »
Stefano Teso · Andrea Bontempelli · Fausto Giunchiglia · Andrea Passerini -
2021 Spotlight: Tractable Regularization of Probabilistic Circuits »
Anji Liu · Guy Van den Broeck -
2022 Poster: Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation »
Zhizhou Ren · Anji Liu · Yitao Liang · Jian Peng · Jianzhu Ma -
2022 : GlanceNets: Interpretable, Leak-proof Concept-based Models »
Emanuele Marconato · Andrea Passerini · Stefano Teso -
2023 Poster: Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts »
Emanuele Marconato · Stefano Teso · Antonio Vergari · Andrea Passerini -
2023 Poster: Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents »
Zihao Wang · Shaofei Cai · Guanzhou Chen · Anji Liu · Xiaojian (Shawn) Ma · Yitao Liang -
2022 : GlanceNets: Interpretable, Leak-proof Concept-based Models »
Emanuele Marconato · Andrea Passerini · Stefano Teso -
2022 Spotlight: GlanceNets: Interpretable, Leak-proof Concept-based Models »
Emanuele Marconato · Andrea Passerini · Stefano Teso -
2022 : Q & A »
Antonio Vergari · YooJung Choi · Robert Peharz -
2022 Tutorial: Probabilistic Circuits: Representations, Inference, Learning and Applications »
Antonio Vergari · YooJung Choi · Robert Peharz -
2022 : Tutorial part 1 »
Antonio Vergari · YooJung Choi · Robert Peharz -
2022 Poster: Semantic Probabilistic Layers for Neuro-Symbolic Learning »
Kareem Ahmed · Stefano Teso · Kai-Wei Chang · Guy Van den Broeck · Antonio Vergari -
2022 Poster: Sparse Probabilistic Circuits via Pruning and Growing »
Meihua Dang · Anji Liu · Guy Van den Broeck -
2022 Poster: GlanceNets: Interpretable, Leak-proof Concept-based Models »
Emanuele Marconato · Andrea Passerini · Stefano Teso -
2021 Poster: Interactive Label Cleaning with Example-based Explanations »
Stefano Teso · Andrea Bontempelli · Fausto Giunchiglia · Andrea Passerini -
2021 Poster: Tractable Regularization of Probabilistic Circuits »
Anji Liu · Guy Van den Broeck -
2020 : Contributed talks 6: Group Fairness by Probabilistic Modeling with Latent Fair Decisions »
YooJung Choi · Guy Van den Broeck -
2020 Poster: Efficient Generation of Structured Objects with Constrained Adversarial Networks »
Luca Di Liello · Pierfrancesco Ardino · Jacopo Gobbi · Paolo Morettin · Stefano Teso · Andrea Passerini -
2019 : Break / Poster Session 1 »
Antonia Marcu · Yao-Yuan Yang · Pascale Gourdeau · Chen Zhu · Thodoris Lykouris · Jianfeng Chi · Mark Kozdoba · Arjun Nitin Bhagoji · Xiaoxia Wu · Jay Nandy · Michael T Smith · Bingyang Wen · Yuege Xie · Konstantinos Pitas · Suprosanna Shit · Maksym Andriushchenko · Dingli Yu · GaĆ«l Letarte · Misha Khodak · Hussein Mozannar · Chara Podimata · James Foulds · Yizhen Wang · Huishuai Zhang · Ondrej Kuzelka · Alexander Levine · Nan Lu · Zakaria Mhammedi · Paul Viallard · Diana Cai · Lovedeep Gondara · James Lucas · Yasaman Mahdaviyeh · Aristide Baratin · Rishi Bommasani · Alessandro Barp · Andrew Ilyas · Kaiwen Wu · Jens Behrmann · Omar Rivasplata · Amir Nazemi · Aditi Raghunathan · Will Stephenson · Sahil Singla · Akhil Gupta · YooJung Choi · Yannic Kilcher · Clare Lyle · Edoardo Manino · Andrew Bennett · Zhi Xu · Niladri Chatterji · Emre Barut · Flavien Prost · Rodrigo Toro Icarte · Arno Blaas · Chulhee Yun · Sahin Lale · YiDing Jiang · Tharun Kumar Reddy Medini · Ashkan Rezaei · Alexander Meinke · Stephen Mell · Gary Kazantsev · Shivam Garg · Aradhana Sinha · Vishnu Lokhande · Geovani Rizk · Han Zhao · Aditya Kumar Akash · Jikai Hou · Ali Ghodsi · Matthias Hein · Tyler Sypherd · Yichen Yang · Anastasia Pentina · Pierre Gillot · Antoine Ledent · Guy Gur-Ari · Noah MacAulay · Tianzong Zhang -
2019 Poster: On Tractable Computation of Expected Predictions »
Pasha Khosravi · YooJung Choi · Yitao Liang · Antonio Vergari · Guy Van den Broeck -
2016 Poster: New Liftable Classes for First-Order Probabilistic Inference »
Seyed Mehran Kazemi · Angelika Kimmig · Guy Van den Broeck · David Poole -
2015 Poster: Tractable Learning for Complex Probability Queries »
Jessa Bekker · Jesse Davis · Arthur Choi · Adnan Darwiche · Guy Van den Broeck -
2013 Poster: On the Complexity and Approximation of Binary Evidence in Lifted Inference »
Guy Van den Broeck · Adnan Darwiche -
2013 Spotlight: On the Complexity and Approximation of Binary Evidence in Lifted Inference »
Guy Van den Broeck · Adnan Darwiche -
2011 Poster: On the Completeness of First-Order Knowledge Compilation for Lifted Probabilistic Inference »
Guy Van den Broeck -
2011 Oral: On the Completeness of First-Order Knowledge Compilation for Lifted Probabilistic Inference »
Guy Van den Broeck