Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces

• URL: http://arxiv.org/abs/2511.06239v1
• Date: Sun, 09 Nov 2025 05:51:03 GMT
• Title: Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
• Authors: Byoungwoo Park, Juho Lee, Guan-Horng Liu,
• Abstract summary: We present an optimal control-based diffusion sampler for infinite-dimensional function spaces.<n>We show that it achieves superior transition path sampling performance across synthetic potential and real molecular systems.
• Score: 22.412483650808728
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning-based methods for sampling from the Gibbs distribution in finite-dimensional spaces have progressed quickly, yet theory and algorithmic design for infinite-dimensional function spaces remain limited. This gap persists despite their strong potential for sampling the paths of conditional diffusion processes, enabling efficient simulation of trajectories of diffusion processes that respect rare events or boundary constraints. In this work, we present the adjoint sampler for infinite-dimensional function spaces, a stochastic optimal control-based diffusion sampler that operates in function space and targets Gibbs-type distributions on infinite-dimensional Hilbert spaces. Our Functional Adjoint Sampler (FAS) generalizes Adjoint Sampling (Havens et al., 2025) to Hilbert spaces based on a SOC theory called stochastic maximum principle, yielding a simple and scalable matching-type objective for a functional representation. We show that FAS achieves superior transition path sampling performance across synthetic potential and real molecular systems, including Alanine Dipeptide and Chignolin.

Related papers

• Stochastic Interpolants in Hilbert Spaces [22.77471216660321]
  interpolants offer a flexible way to bridge arbitrary distributions.<n>This paper establishes a rigorous framework for Hilbert interpolants in infinite-dimensional spaces.<n>We demonstrate the effectiveness of the proposed framework for conditional generation.
  arXiv  Detail & Related papers  (2026-02-02T11:44:34Z)
• Guided Diffusion Sampling on Function Spaces with Applications to PDEs [112.09025802445329]
  We propose a general framework for conditional sampling in PDE-based inverse problems.<n>This is accomplished by a function-space diffusion model and plug-and-play guidance for conditioning.<n>Our method achieves an average 32% accuracy improvement over state-of-the-art fixed-resolution diffusion baselines.
  arXiv  Detail & Related papers  (2025-05-22T17:58:12Z)
• Stochastic Optimal Control for Diffusion Bridges in Function Spaces [13.544676987441441]
  We present a theory of optimal control tailored to infinite-dimensional spaces.<n>We show how Doob's $h$-transform can be derived from the SOC perspective and expanded to infinite dimensions.<n>We propose two applications: learning bridges between two infinite-dimensional distributions and generative models for sampling from an infinite-dimensional distribution.
  arXiv  Detail & Related papers  (2024-05-31T05:42:47Z)
• Space-Time Diffusion Bridge [0.4527270266697462]
  We introduce a novel method for generating new synthetic samples independent and identically distributed from real probability distributions. We use space-time mixing strategies that extend across temporal and spatial dimensions. We validate the efficacy of our space-time diffusion approach with numerical experiments.
  arXiv  Detail & Related papers  (2024-02-13T23:26:11Z)
• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• $\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States [13.75813166759549]
  $infty$-Diff is a generative diffusion model defined in an infinite-dimensional Hilbert space. By training on randomly sampled subsets of coordinates, we learn a continuous function for arbitrary resolution sampling.
  arXiv  Detail & Related papers  (2023-03-31T17:58:08Z)
• Continuous percolation in a Hilbert space for a large system of qubits [58.720142291102135]
  The percolation transition is defined through the appearance of the infinite cluster. We show that the exponentially increasing dimensionality of the Hilbert space makes its covering by finite-size hyperspheres inefficient. Our approach to the percolation transition in compact metric spaces may prove useful for its rigorous treatment in other contexts.
  arXiv  Detail & Related papers  (2022-10-15T13:53:21Z)
• Optimal Scaling for Locally Balanced Proposals in Discrete Spaces [65.14092237705476]
  We show that efficiency of Metropolis-Hastings (M-H) algorithms in discrete spaces can be characterized by an acceptance rate that is independent of the target distribution. Knowledge of the optimal acceptance rate allows one to automatically tune the neighborhood size of a proposal distribution in a discrete space, directly analogous to step-size control in continuous spaces.
  arXiv  Detail & Related papers  (2022-09-16T22:09:53Z)
• Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings [97.12538243736705]
  We study reinforcement learning with function approximation for large-scale Partially Observable Decision Processes (POMDPs) Our algorithm provably scales to large-scale POMDPs.
  arXiv  Detail & Related papers  (2022-06-24T05:13:35Z)
• Concentration analysis of multivariate elliptic diffusion processes [0.0]
  We prove concentration inequalities and associated PAC bounds for continuous- and discrete-time additive functionals. Our analysis relies on an approach via the Poisson equation allowing us to consider a very broad class of subexponentially ergodic processes.
  arXiv  Detail & Related papers  (2022-06-07T14:15:05Z)

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.