Random-Bridges as Stochastic Transports for Generative Models

• URL: http://arxiv.org/abs/2512.14190v1
• Date: Tue, 16 Dec 2025 08:37:19 GMT
• Title: Random-Bridges as Stochastic Transports for Generative Models
• Abstract summary: This paper motivates the use of random-bridges -- conditioned processes to take target distributions at fixed time inception.<n>We show how one can start from general probabilistic statements and then branch out into specific representations for learning and simulation algorithms.
• Score: 1.2599533416395763
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper motivates the use of random-bridges -- stochastic processes conditioned to take target distributions at fixed timepoints -- in the realm of generative modelling. Herein, random-bridges can act as stochastic transports between two probability distributions when appropriately initialized, and can display either Markovian or non-Markovian, and either continuous, discontinuous or hybrid patterns depending on the driving process. We show how one can start from general probabilistic statements and then branch out into specific representations for learning and simulation algorithms in terms of information processing. Our empirical results, built on Gaussian random bridges, produce high-quality samples in significantly fewer steps compared to traditional approaches, while achieving competitive Frechet inception distance scores. Our analysis provides evidence that the proposed framework is computationally cheap and suitable for high-speed generation tasks.

Related papers

• Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields [6.198432039341305]
  We introduce Random Process (RP) Flow, a Flow Matching-based framework that represents the vector field as a neural implicit function.<n>RP Flow uses Random Fourier Features to learn an implicit signal representation that can be queried at any arbitrary location from a limited set of observations.<n>Our empirical results demonstrate that this framework generates realistic samples along with calibrated uncertainty estimates, even under challenging conditions such as high frequency, high sparsity, or high dimensionality.
  arXiv  Detail & Related papers  (2026-05-27T15:31:29Z)
• Latent Process Generator Matching [0.0]
  We introduce latent process generator matching, a general framework that treats the observed generative state as a deterministic image.<n>We show that in this setting one may learn the generator of a process on the image space which has the same one-time marginal distributions as the projected process.
  arXiv  Detail & Related papers  (2026-05-19T22:49:05Z)
• Deterministic Mode Proposals: An Efficient Alternative to Generative Sampling for Ambiguous Segmentation [3.5493798890908113]
  We introduce a deterministic framework that efficiently produces a fixed-size set of proposal masks in a single forward pass.<n>Our approach significantly reduces inference time while achieving higher ground-truth coverage than existing generative models.<n>We demonstrate that our model can be trained without knowing the full distribution of outcomes, making it applicable to real-world datasets.
  arXiv  Detail & Related papers  (2026-03-20T17:59:26Z)
• Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models [66.60042743462175]
  We present a copula-based approach to efficiently generate accurate, correlated sample paths from time series foundation models.<n>Our approach generates correlated sample paths orders of magnitude faster than autoregressive sampling.
  arXiv  Detail & Related papers  (2025-10-02T17:08:58Z)
• Accelerated Diffusion Models via Speculative Sampling [89.43940130493233]
  Speculative sampling is a popular technique for accelerating inference in Large Language Models.<n>We extend speculative sampling to diffusion models, which generate samples via continuous, vector-valued Markov chains.<n>We propose various drafting strategies, including a simple and effective approach that does not require training a draft model.
  arXiv  Detail & Related papers  (2025-01-09T16:50:16Z)
• Probabilistic Forecasting of Real-Time Electricity Market Signals via Interpretable Generative AI [41.99446024585741]
  We present WIAE-GPF, a Weak Innovation AutoEncoder-based Generative Probabilistic Forecasting architecture. A novel learning algorithm with structural convergence guarantees is proposed, ensuring that the generated forecast samples match the ground truth conditional probability distribution.
  arXiv  Detail & Related papers  (2024-03-09T00:41:30Z)
• Logistic-beta processes for dependent random probabilities with beta marginals [58.91121576998588]
  We propose a novel process called the logistic-beta process, whose logistic transformation yields a process with common beta marginals.<n>We show how the proposed logistic-beta process can be used to design computationally tractable dependent nonparametric models.
  arXiv  Detail & Related papers  (2024-02-10T21:41:32Z)
• Stable generative modeling using Schrödinger bridges [0.22499166814992438]
  We propose a generative model combining Schr"odinger bridges and Langevin dynamics. Our framework can be naturally extended to generate conditional samples and to Bayesian inference problems.
  arXiv  Detail & Related papers  (2024-01-09T06:15:45Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks [0.0]
  Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Here we quantitatively test this approach by applying it to a prototypical process on a lattice. Importantly, the discreteness of the model is retained despite the noise.
  arXiv  Detail & Related papers  (2023-05-25T10:41:02Z)
• A Flow-Based Generative Model for Rare-Event Simulation [0.483420384410068]
  We present a method in which a Normalizing Flow generative model is trained to simulate samples directly from a conditional distribution. We illustrate that by simulating directly from a rare-event distribution significant insight can be gained into the way rare events happen.
  arXiv  Detail & Related papers  (2023-05-13T08:25:57Z)
• Provably Convergent Schr\"odinger Bridge with Applications to Probabilistic Time Series Imputation [21.27702285561771]
  We present a first convergence analysis of the Schr"odinger bridge algorithm based on approximated projections. As for its practical applications, we apply SBP to probabilistic time series imputation by generating missing values conditioned on observed data.
  arXiv  Detail & Related papers  (2023-05-12T04:39:01Z)
• Applying Regularized Schr\"odinger-Bridge-Based Stochastic Process in Generative Modeling [0.0]
  This study tries to reduce the number of timesteps and training time required and proposed regularization terms to make bidirectional processes consistent with a reduced number of timesteps. Applying this regularization to various tasks, the possibility of generative modeling based on a process with faster sampling speed could be confirmed.
  arXiv  Detail & Related papers  (2022-08-15T11:52:33Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• Efficiently Sampling Functions from Gaussian Process Posteriors [76.94808614373609]
  We propose an easy-to-use and general-purpose approach for fast posterior sampling. We demonstrate how decoupled sample paths accurately represent Gaussian process posteriors at a fraction of the usual cost.
  arXiv  Detail & Related papers  (2020-02-21T14:03:16Z)

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.