On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions

• URL: http://arxiv.org/abs/2608.31120v1
• Date: Mon, 31 Aug 2026 17:32:21 GMT
• Title: On the Complexity of the Compatibility Problem for Succinctly Encoded Conditional Distributions
• Abstract summary: This paper investigates the trade-offs implicit in probabilistic models used in machine learning.<n>A pair of conditional distributions p(x|y) and p(y|x) may not be compatible with any joint distribution p(x,y)<n>For discrete random variables, when the conditionals are encoded as probability tables, the compatibility problem has a known solution.
• Score: 6.582423386446727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The motivation for this paper is the investigation of the trade-offs implicit in probabilistic models used in machine learning. Models are often used to make predictions in the form of conditional probabilities. However, a pair of conditional distributions p(x|y) and p(y|x) may not be compatible with any joint distribution p(x,y). Given two such conditionals, determining if there exists a compatible joint is known as the compatibility problem. For discrete random variables, when the conditionals are encoded as probability tables, the compatibility problem has a known solution, which is computationally tractable. In this paper, we formalise and study a succinct version of the problem, encoding conditional distributions as arithmetic circuits. This is applicable to practical applications of probabilistic modelling in high-dimensional settings, including neural network models. We show that, for succinct circuit representations of conditionals, the compatibility problem is intractable. In the case that all probabilities are non-zero, the problem is co-NP-complete. In the case that probabilities can be zero, we give examples to demonstrate that several notions of compatibility can be distinguished, and we prove that multiple versions of the problem are PSPACE-complete. Furthermore, we show that, assuming the polynomial hierarchy does not collapse, there exist compatible succinct conditionals whose joint cannot be expressed succinctly. Implications of these results for probabilistic modelling and machine learning are discussed.

Related papers

• How to Verify Consistency of Probabilistic Claims [49.47758039235095]
  We construct an interactive PCP to prove a predictive model's consistency.<n>We show how a small additive-soundness gap removes dependence on B.<n>We view our interactive PCP as a first step toward predictive models to prove their own consistency.
  arXiv  Detail & Related papers  (2026-08-11T17:41:39Z)
• Probabilistic and Causal Satisfiability: Constraining the Model [0.49399484784577985]
  We study the complexity of satisfiability problems in probabilistic and causal reasoning.<n>The basic terms are probabilities of propositional formulas over atomic events.<n>We extend this line of work by adding two new dimensions to the problem by constraining the models.
  arXiv  Detail & Related papers  (2025-04-28T16:14:06Z)
• User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems [49.75149094527068]
  We show that diffusion models can be adapted to make predictions and provide uncertainty quantification for chaotic dynamical systems. We develop a probabilistic approximation scheme for the conditional score function which converges to the true distribution as the noise level decreases. We are able to sample conditionally on nonlinear userdefined events at inference time, and matches data statistics even when sampling from the tails of the distribution.
  arXiv  Detail & Related papers  (2023-06-13T03:42:03Z)
• Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach [7.059472280274009]
  We present an exact Bayesian inference method for discrete statistical models. We use a probabilistic programming language that supports discrete and continuous sampling, discrete observations, affine functions, (stochastic) branching, and conditioning on discrete events. Our inference method is provably correct and fully automated.
  arXiv  Detail & Related papers  (2023-05-26T16:09:59Z)
• The Hardness of Reasoning about Probabilities and Causality [5.190207094732672]
  We study languages capable of expressing quantitative probabilistic reasoning and do-calculus reasoning for causal effects. The main contribution of this work is establishing the exact computational complexity of satisfiability problems. We introduce a new natural complexity class, named succ$exists$R, which can be viewed as a succinct variant of the well-studied class $exists$R.
  arXiv  Detail & Related papers  (2023-05-16T15:01:22Z)
• Marginal Inference queries in Hidden Markov Models under context-free grammar constraints [0.348097307252416]
  We address the question of computing the likelihood of context-free grammars (CFGs) in Hidden Models (HMMs) We show that the problem is NP-Hard, even with the promise that CFG has a degree of ambiguity less than or equal to 2. We then propose a fully randomized approximation scheme to approximate the likelihood for the case of ambiguous CFGs.
  arXiv  Detail & Related papers  (2022-06-26T12:44:18Z)
• On the Generative Utility of Cyclic Conditionals [103.1624347008042]
  We study whether and how can we model a joint distribution $p(x,z)$ using two conditional models $p(x|z)$ that form a cycle. We propose the CyGen framework for cyclic-conditional generative modeling, including methods to enforce compatibility and use the determined distribution to fit and generate data.
  arXiv  Detail & Related papers  (2021-06-30T10:23:45Z)
• 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)
• Tractable Inference in Credal Sentential Decision Diagrams [116.6516175350871]
  Probabilistic sentential decision diagrams are logic circuits where the inputs of disjunctive gates are annotated by probability values. We develop the credal sentential decision diagrams, a generalisation of their probabilistic counterpart that allows for replacing the local probabilities with credal sets of mass functions. For a first empirical validation, we consider a simple application based on noisy seven-segment display images.
  arXiv  Detail & Related papers  (2020-08-19T16:04:34Z)
• Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators [72.62940905965267]
  Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. Are CF-INNs universal approximators for invertible functions? We prove a general theorem to show the equivalence of the universality for certain diffeomorphism classes.
  arXiv  Detail & Related papers  (2020-06-20T02:07:37Z)

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.