A Generative Sampler for distributions with possible discrete parameter based on Reversibility

• URL: http://arxiv.org/abs/2603.09251v1
• Date: Tue, 10 Mar 2026 06:32:51 GMT
• Title: A Generative Sampler for distributions with possible discrete parameter based on Reversibility
• Abstract summary: We propose a unified, target-gradient-free generative sampling framework applicable across diverse state spaces.<n>We minimize the Maximum Mean Discrepancy (MMD) between the joint distributions of forward and backward Markov trajectories.<n> Experiments show that our framework accurately reproduces thermodynamic observables and captures mode-switching behavior across all regimes.
• Score: 9.349846971147256
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning to sample from complex unnormalized distributions is a fundamental challenge in computational physics and machine learning. While score-based and variational methods have achieved success in continuous domains, extending them to discrete or mixed-variable systems remains difficult due to ill-defined gradients or high variance in estimators. We propose a unified, target-gradient-free generative sampling framework applicable across diverse state spaces. Building on the fact that detailed balance implies the time-reversibility of the equilibrium stochastic process, we enforce this symmetry as a statistical constraint. Specifically, using a prescribed physical transition kernel (such as Metropolis-Hastings), we minimize the Maximum Mean Discrepancy (MMD) between the joint distributions of forward and backward Markov trajectories. Crucially, this training procedure relies solely on energy evaluations via acceptance ratios, circumventing the need for target score functions or continuous relaxations. We demonstrate the versatility of our method on three distinct benchmarks: (1) a continuous multi-modal Gaussian mixture, (2) the discrete high-dimensional Ising model, and (3) a challenging hybrid system coupling discrete indices with continuous dynamics. Experiments show that our framework accurately reproduces thermodynamic observables and captures mode-switching behavior across all regimes, offering a physically grounded and universally applicable alternative for equilibrium sampling.

Related papers

• Purification of a monitored qubit: exact path-integral solution [0.0]
  We investigate the purification dynamics of a single qubit under continuous in time monitoring.<n>We show that for initial mixed states, the dynamics reduce to a multiplicative Langevin equation for a single parameter representing the state's purity.<n>Our analytical results reveal that purification is characterized by a dynamical crossover from a diffusion dominated regime to a measurement dominated regime, visible in the emergence of a bimodal state distribution.
  arXiv  Detail & Related papers  (2026-05-12T21:55:51Z)
• SymDrift: One-Shot Generative Modeling under Symmetries [19.741742157466888]
  We show that drifting models face a symmetry-specific challenge, since an equivariant generator does not generally produce the same drifting field as the one obtained from the symmetrized target distribution.<n>We introduce two complementary strategies: (i) a symmetrized drift in coordinate space based on optimal alignment, and (ii) a $G$-invariant embedding that removes symmetry ambiguity by construction.<n>By enabling one-shot inference, SymDrift reduces computational overhead by up to 40$times$ compared to existing baselines.
  arXiv  Detail & Related papers  (2026-05-07T12:38:44Z)
• Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching [38.70740405520393]
  Bridge Matching Sampler (BMS) enables learning a transport map between arbitrary prior and target distributions with a single, scalable, and stable objective.<n>We demonstrate that our method enables sampling at unprecedented scales while preserving mode diversity, achieving state-of-the-art results on complex synthetic densities and high-dimensional molecular benchmarks.
  arXiv  Detail & Related papers  (2026-02-28T08:00:38Z)
• Stochastic unravelings for trace-nonpreserving open quantum system dynamics [0.0]
  We introduce a general framework that extends piecewise-deterministic unravelings to arbitrary trace-nonpreserving master equations.<n>Our approach includes, as special cases, unravelings of arbitrary dynamics in the Heisenberg picture.<n>It is compatible with different unraveling schemes and with reverse jumps in the non-Markovian regime.
  arXiv  Detail & Related papers  (2025-11-19T15:10:27Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [56.442307356162864]
  We study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework.<n>We introduce a discrete-time sampling algorithm in the general state space $[S]d$ that utilizes score estimators at predefined time points.<n>Our convergence analysis employs a Girsanov-based method and establishes key properties of the discrete score function.
  arXiv  Detail & Related papers  (2024-10-03T09:07:13Z)
• 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)
• Distributionally Robust Model-based Reinforcement Learning with Large State Spaces [55.14361269378122]
  Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. We study distributionally robust Markov decision processes with continuous state spaces under the widely used Kullback-Leibler, chi-square, and total variation uncertainty sets. We propose a model-based approach that utilizes Gaussian Processes and the maximum variance reduction algorithm to efficiently learn multi-output nominal transition dynamics.
  arXiv  Detail & Related papers  (2023-09-05T13:42:11Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)
• An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games [16.95910326345246]
  We consider the problem of computing mixed Nash equilibria of two-player zero-sum games with continuous sets of pure strategies and with first-order access to the payoff function.<n>This problem arises for example in game-inspired machine learning applications, such as distributionally-robust learning.<n>We introduce and analyze a particle-based method that enjoys guaranteed local convergence for this problem.
  arXiv  Detail & Related papers  (2022-11-02T17:03:40Z)
• A Dynamical System View of Langevin-Based Non-Convex Sampling [44.002384711340966]
  Non- sampling is a key challenge in machine learning, central to non-rate optimization in deep learning as well as to approximate its significance. Existing guarantees typically only hold for the averaged distances rather than the more desirable last-rate iterates. We develop a new framework that lifts the above issues by harnessing several tools from the theory systems.
  arXiv  Detail & Related papers  (2022-10-25T09:43:36Z)
• The Connection between Discrete- and Continuous-Time Descriptions of Gaussian Continuous Processes [60.35125735474386]
  We show that discretizations yielding consistent estimators have the property of invariance under coarse-graining' This result explains why combining differencing schemes for derivatives reconstruction and local-in-time inference approaches does not work for time series analysis of second or higher order differential equations.
  arXiv  Detail & Related papers  (2021-01-16T17:11:02Z)
• Stochastic Normalizing Flows [2.323220706791067]
  We show that normalizing flows can be used to learn the transformation of a simple prior distribution. We derive an efficient training procedure by which both the sampler's and the flow's parameters can be optimized end-to-end. We illustrate the representational power, sampling efficiency and correctness of SNFs on several benchmarks including applications to molecular sampling systems in equilibrium.
  arXiv  Detail & Related papers  (2020-02-16T23:29:32Z)

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.