One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators

• URL: http://arxiv.org/abs/2605.06873v2
• Date: Mon, 11 May 2026 20:41:42 GMT
• Title: One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operators
• Abstract summary: Probabilistic conditioning is concerned with the identification of a distribution of a random variable $X$ given a random variable $Y$.<n>This paper introduces a novel perspective: we propose to solve the conditioning problem by identifying a single operator that maps any joint density to its conditional.<n>Our proof relies on new results establishing continuity of the conditioning operator over suitable classes of densities.
• Score: 4.421502930383329
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Probabilistic conditioning is concerned with the identification of a distribution of a random variable $X$ given a random variable $Y$. It is a cornerstone of scientific and engineering applications where modeling uncertainty is key. This problem has traditionally been addressed in machine learning by directly learning the conditional distribution of a fixed joint distribution. This paper introduces a novel perspective: we propose to solve the conditioning problem by identifying a single operator that maps any joint density to its conditional, thus amortizing over joint-conditional pairs. We establish that the conditioning operator can be approximated to arbitrary accuracy by neural operators. Our proof relies on new results establishing continuity of the conditioning operator over suitable classes of densities. Finally, we learn the conditioning map for a class of Gaussian mixtures using neural operators, illustrating the promise of our framework. This work provides the theoretical underpinnings for general-purpose, amortized methods for probabilistic conditioning, such as foundation models for Bayesian inference.

Related papers

• Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators [0.0]
  Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and machine learning.<n>We show that such mapping properties are characterized by the regularity of the Radon--Nikodym density of the conditional law.<n>The resulting framework offers a unified perspective on conditional expectation operators across probability, operator theory, kernel methods, and dynamics.
  arXiv  Detail & Related papers  (2026-08-06T15:22:33Z)
• Learning operators on labelled conditional distributions with applications to mean field control of non exchangeable systems [3.441021278275805]
  We study the approximation of operators acting on probability measures on a product space with prescribed marginal.<n>Our main theoretical result establishes a universal approximation theorem for continuous operators on $cal M_$.<n>We introduce a sampling strategy for generating training measures in $cal M_$, enabling practical learning of such conditional mean-field operators.
  arXiv  Detail & Related papers  (2026-03-23T08:13:21Z)
• Nonparametric estimation of conditional probability distributions using a generative approach based on conditional push-forward neural networks [0.0]
  We introduce conditional push-forward neural networks (CPFN), a generative framework for conditional distribution estimation.<n>CPFN learns a map $varphi=varphi(x,u)$ such that $varphi(x,U)$ and $Y|X=x$ follow approximately the same law.<n>It is trained via an objective function derived from a Kullback-Leibler formulation, without requiring invertibility or adversarial training.
  arXiv  Detail & Related papers  (2025-11-18T12:59:20Z)
• MAP Estimation with Denoisers: Convergence Rates and Guarantees [37.88502562012743]
  We show that a simple algorithm converges to the proximal operator under a log-concavity assumption on the prior $p$.<n>We show that this algorithm can be interpreted as a gradient descent on smoothed proximal objectives.
  arXiv  Detail & Related papers  (2025-07-21T08:59:33Z)
• Score-Based Model for Low-Rank Tensor Recovery [49.158601255093416]
  Low-rank tensor decompositions (TDs) provide an effective framework for multiway data analysis.<n>Traditional TD methods rely on predefined structural assumptions, such as CP or Tucker decompositions.<n>We propose a score-based model that eliminates the need for predefined structural or distributional assumptions.
  arXiv  Detail & Related papers  (2025-06-27T15:05:37Z)
• Conditional Pseudo-Reversible Normalizing Flow for Surrogate Modeling in Quantifying Uncertainty Propagation [11.874729463016227]
  We introduce a conditional pseudo-reversible normalizing flow for constructing surrogate models of a physical model polluted by additive noise. The training process utilizes dataset consisting of input-output pairs without requiring prior knowledge about the noise and the function. Our model, once trained, can generate samples from any conditional probability density functions whose high probability regions are covered by the training set.
  arXiv  Detail & Related papers  (2024-03-31T00:09:58Z)
• Gaussian Mixture Models for Affordance Learning using Bayesian Networks [50.18477618198277]
  Affordances are fundamental descriptors of relationships between actions, objects and effects. This paper approaches the problem of an embodied agent exploring the world and learning these affordances autonomously from its sensory experiences.
  arXiv  Detail & Related papers  (2024-02-08T22:05:45Z)
• CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks [58.29502185344086]
  In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks. It is important to provide provable guarantees for deep learning models against semantically meaningful input transformations. We propose a new universal probabilistic certification approach based on Chernoff-Cramer bounds.
  arXiv  Detail & Related papers  (2021-09-22T12:46:04Z)
• 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)
• 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)
• Consistency Regularization for Certified Robustness of Smoothed Classifiers [89.72878906950208]
  A recent technique of randomized smoothing has shown that the worst-case $ell$-robustness can be transformed into the average-case robustness. We found that the trade-off between accuracy and certified robustness of smoothed classifiers can be greatly controlled by simply regularizing the prediction consistency over noise.
  arXiv  Detail & Related papers  (2020-06-07T06:57:43Z)

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.