Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators

• URL: http://arxiv.org/abs/2608.06155v1
• Date: Thu, 06 Aug 2026 15:22:33 GMT
• Title: Verifiable Regularity Criterion for Conditional Expectation Operators and Conditional Mean Embeddings with Applications to Nonparametric Regression, Bayesian Inverse Problems, and Koopman Operators
• Abstract summary: 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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Conditional expectation operators (CEOs) and their associated conditional mean embeddings (CMEs) play a central role across applied mathematics and machine learning, appearing in nonparametric regression, Bayesian inverse problems, and Koopman operator theory. A fundamental question is when a CEO maps a function space on $\mathcal{Y}$ into a prescribed function space on $\mathcal{X}$, particularly a reproducing kernel Hilbert space (RKHS). We show that such mapping properties are characterized by the regularity of the Radon--Nikodym density of the conditional law, and establish a simple, verifiable sufficient condition under which the CEO is bounded and Hilbert--Schmidt. For RKHSs norm-equivalent to Sobolev spaces, this condition reduces to Sobolev regularity of the conditional density. The result yields a direct route to validate CME representations and error bounds for Galerkin-type and CME-based estimators. We verify the regularity condition in three settings: nonparametric regression, Bayesian inverse problems, and Koopman operator theory for stochastic dynamical systems. We show in each case that classical regularity results on the underlying probabilistic model imply the required mapping properties. The resulting framework offers a unified perspective on conditional expectation operators across probability, operator theory, kernel methods, and stochastic dynamics.

Related papers

• Operator Calculus for Population-Based Optimization: A Mean-Field Convergence Theory [0.2770822269241973]
  Population-based and distributional optimization methods are widely used for nonreactional problems.<n>We provide a toolkit for convergence of composite composite algorithms.
  arXiv  Detail & Related papers  (2026-06-12T09:16:58Z)
• Classical Simulability from Operator Entanglement Scaling [0.0]
  Local-operator entanglement (LOE) quantifies the nonlocal structure of Heisenberg operators and serves as a diagnostic of many-body chaos.<n>We provide rigorous bounds showing when an operator can be well-approximated by a matrix-product operator (MPO), given scaling of its LOE $$-Rényi entropies.<n>Our results put on firm footing the expectation that a low operator entanglement implies efficient tensor network representability.
  arXiv  Detail & Related papers  (2026-03-05T20:18:05Z)
• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Stabilizing Fixed-Point Iteration for Markov Chain Poisson Equations [49.702772230127465]
  We study finite-state Markov chains with $n$ states and transition matrix $P$.<n>We show that all non-decaying modes are captured by a real peripheral invariant subspace $mathcalK(P)$, and that the induced operator on the quotient space $mathbbRn/mathcalK(P) is strictly contractive, yielding a unique quotient solution.
  arXiv  Detail & Related papers  (2026-01-31T02:57:01Z)
• Graph-based Clustering Revisited: A Relaxation of Kernel $k$-Means Perspective [73.18641268511318]
  We propose a graph-based clustering algorithm that only relaxes the orthonormal constraint to derive clustering results.<n>To ensure a doubly constraint into a gradient, we transform the non-negative constraint into a class probability parameter.
  arXiv  Detail & Related papers  (2025-09-23T09:14:39Z)
• Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems [4.2223436389469144]
  Langevin dynamics driven by score-based generative models (SGMs) acting as priors, formulated directly in function space.<n>We derive, for the first time, error estimates that explicitly depend on the approximation error of the score.<n>As a consequence, we obtain sufficient conditions for global convergence in Kullback-Leibler divergence on the underlying function space.
  arXiv  Detail & Related papers  (2025-05-23T18:12:04Z)
• Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels [5.663076715852465]
  We investigate regularized convergence encoder descent (SGD) algorithms for estimating nonlinear operators from a Polish space to a separable Hilbert space.<n>We present a new technique for deriving bounds with high probability for general SGD schemes.
  arXiv  Detail & Related papers  (2025-04-25T08:57:38Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• Optimal Recovery from Inaccurate Data in Hilbert Spaces: Regularize, but what of the Parameter? [6.85316573653194]
  This article considers a model assumption based on approximability in the framework of Hilbert spaces. It also incorporates observational inaccuracies via additive errors bounded in $ell$. It fills the gap in both a local scenario and a global scenario.
  arXiv  Detail & Related papers  (2021-11-04T03:02:55Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)

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.