Probabilistic Circuits as Reasoning Machines in Artificial Intelligence (Part I)

• URL: http://arxiv.org/abs/2608.16565v1
• Date: Mon, 17 Aug 2026 13:29:05 GMT
• Title: Probabilistic Circuits as Reasoning Machines in Artificial Intelligence (Part I)
• Abstract summary: This thesis studies probabilistic circuits (PCs) as a powerful and tractable framework for reasoning and learning under uncertainty in AI.<n>It first advocates for probability as a core language for AI, emphasizing its connections to logic and information theory.<n>This thesis synthesizes a decade of research across foundations, developments, and empirical validation of PCs.
• Score: 4.867681546866858
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This cumulative habilitation thesis studies probabilistic circuits (PCs) as a powerful and tractable framework for reasoning and learning under uncertainty in artificial intelligence (AI). It first advocates for probability as a core language for AI, emphasizing its connections to logic and information theory; the conceptual simplicity of probabilistic reasoning---based primarily on the sum and product rules; the parallels between probabilistic inference and human cognition; and the role of probability in optimal decision making. However, probability also faces significant computational challenges, as probabilistic inference is NP-hard in almost all probabilistic models. PCs address these challenges through structural constraints that ensure exact computation of a wide range of inference queries in polynomial time, such as marginals, conditionals, most probable explanations, expectations, and more advanced inference tasks. This thesis synthesizes a decade of research across foundations, algorithmic developments, and empirical validation of PCs. Key contributions highlighted in this work are foundational theory of PCs, Bayesian approaches for learning PCs, scalable implementations and integration with deep learning, hybrid models that combine PCs with intractable models, and connections with symbolic machine learning paradigms. This is the first part of my Habilitation Thesis. The second part is omitted, as it comprises the cumulative part of the thesis and has been published at various venues (see Chapter 5).

Related papers

• From Atomic to Composite: Reinforcement Learning Enables Generalization in Complementary Reasoning [83.94543243783285]
  We study Complementary Reasoning, a complex task that requires integrating internal parametric knowledge with external contextual information.<n>We find that RL acts as a reasoning synthesizer rather than a probability amplifier.
  arXiv  Detail & Related papers  (2025-12-01T18:27:25Z)
• Tractable Representation Learning with Probabilistic Circuits [30.116247936061395]
  Probabilistic circuits (PCs) are powerful probabilistic models that enable exact and tractable inference.<n>While dominant in neural networks, representation learning with PCs remains underexplored.<n>We introduce autoencoding probabilistic circuits (APCs), a novel framework leveraging the tractability of PCs to model probabilistic embeddings explicitly.
  arXiv  Detail & Related papers  (2025-07-06T13:17:16Z)
• Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models [6.922021128239465]
  Recent advances in AI have been driven by the capabilities of large language models (LLMs) This paper introduces a framework that is both theoretical and practical, aimed at assessing how effectively LLMs are able to replicate real-world reasoning mechanisms.
  arXiv  Detail & Related papers  (2024-08-15T15:19:11Z)
• Pruning-Based Extraction of Descriptions from Probabilistic Circuits [5.322838001065884]
  We use a probabilistic circuit to learn a concept from positively labelled and unlabelled examples. These circuits form an attractive tractable model for this task, but it is challenging for a domain expert to inspect and analyse them. We propose to resolve this by converting a learned probabilistic circuit into a logic-based discriminative model.
  arXiv  Detail & Related papers  (2023-11-22T13:19:45Z)
• Brain-inspired Computational Intelligence via Predictive Coding [73.42407863671565]
  Predictive coding (PC) has shown promising properties that make it potentially valuable for the machine learning community.<n>PC-like algorithms are starting to be present in multiple sub-fields of machine learning and AI at large.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• Probabilistic unifying relations for modelling epistemic and aleatoric uncertainty: semantics and automated reasoning with theorem proving [0.3441021278275805]
  Probabilistic programming combines general computer programming, statistical inference, and formal semantics. ProbURel is based on Hehner's predicative probabilistic programming, but there are several obstacles to the broader adoption of his work. Our contributions include the formalisation of relations using Unifying Theories of Programming (UTP) and probabilities outside the brackets. We demonstrate our work with six examples, including problems in robot localisation, classification in machine learning, and the termination of probabilistic loops.
  arXiv  Detail & Related papers  (2023-03-16T23:36:57Z)
• Logical Credal Networks [87.25387518070411]
  This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability. We investigate its performance on maximum a posteriori inference tasks, including solving Mastermind games with uncertainty and detecting credit card fraud.
  arXiv  Detail & Related papers  (2021-09-25T00:00:47Z)
• Online Learning Probabilistic Event Calculus Theories in Answer Set Programming [70.06301658267125]
  Event Recognition (CER) systems detect occurrences in streaming time-stamped datasets using predefined event patterns. We present a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of rules weighted in the Event Calculus. Our results demonstrate the superiority of our novel approach, both terms efficiency and predictive.
  arXiv  Detail & Related papers  (2021-03-31T23:16:29Z)
• Probabilistic Generating Circuits [50.98473654244851]
  We propose probabilistic generating circuits (PGCs) for their efficient representation. PGCs are not just a theoretical framework that unifies vastly different existing models, but also show huge potential in modeling realistic data. We exhibit a simple class of PGCs that are not trivially subsumed by simple combinations of PCs and DPPs, and obtain competitive performance on a suite of density estimation benchmarks.
  arXiv  Detail & Related papers  (2021-02-19T07:06:53Z)
• Paraconsistent Foundations for Probabilistic Reasoning, Programming and Concept Formation [0.0]
  It is argued that 4-valued paraconsistent truth values (called here "p-bits") can serve as a conceptual, mathematical and practical foundation for highly AI-relevant forms of probabilistic logic and programming and concept formation. It is shown that appropriate averaging-across-situations and renormalization of 4-valued p-bits operating in accordance with Constructible Duality (CD) logic yields PLN (Probabilistic Logic Networks) strength-and-confidence truth values.
  arXiv  Detail & Related papers  (2020-12-28T20:14:49Z)
• General stochastic separation theorems with optimal bounds [68.8204255655161]
  Phenomenon of separability was revealed and used in machine learning to correct errors of Artificial Intelligence (AI) systems and analyze AI instabilities. Errors or clusters of errors can be separated from the rest of the data. The ability to correct an AI system also opens up the possibility of an attack on it, and the high dimensionality induces vulnerabilities caused by the same separability.
  arXiv  Detail & Related papers  (2020-10-11T13:12:41Z)
• Quantum Bayesian decision-making* [0.0]
  It proposes a completely quantum mechanical decision-making process with a proven computational advantage. A prototype implementation in Qiskit (a Python-based program development kit for the IBM Q machine) is discussed as a proof-of-concept.
  arXiv  Detail & Related papers  (2020-10-05T15:19:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.