Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers

• URL: http://arxiv.org/abs/2605.16126v1
• Date: Fri, 15 May 2026 16:11:10 GMT
• Title: Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schrödinger Samplers
• Abstract summary: Flow matching and Schrdinger bridges define probability, yet their inference grids are usually or inherited from one-endpoint diffusion.<n>We derive a conditional-marginal entropy-rate objective for bridge-aware discretization, separating endpoint-conditioned bridge geometry from marginal flow evolution.<n>On EDM/CIFAR-10, the entropic time-discretization gives the best tested five-step FID (186.3 pm 4.0 versus 200.5 pm 2.9 for linear and 238.0 pm 5.3 for cosine)
• Score: 68.9946633641494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few function evaluations. Flow matching and Schrödinger bridges define probability paths, yet their inference grids are usually heuristic or inherited from one-endpoint diffusion. We derive a conditional-marginal entropy-rate objective for bridge-aware discretization, separating endpoint-conditioned bridge geometry from marginal flow evolution, and use it to build a training-free entropic inference-time scheduler from first principles. For Gaussian Brownian bridges this rate is closed-form and U-shaped, motivating boundary-heavy nonuniform grids. On trained two-dimensional bridge/flow models, the estimated profile recovers the predicted shape and improves 10-step ODE-Heun MMD over linear by 18.1%, with a paired 22.7% SDE-Heun improvement in the same low-NFE sweep. On EDM/CIFAR-10, the entropic time-discretization gives the best tested five-step FID (186.3 \pm 4.0 versus 200.5 \pm 2.9 for linear and 238.0 \pm 5.3 for cosine). On AlphaFlow protein generation, entropic conditional-marginal (cond-marg) scheduling shows advantage in low-NFE regimes on both CAMEO22 and ATLAS benchmarks. These results support entropy-rate scheduling as a practical low-budget allocation signal for high-dimensional bridge and flow samplers.

Related papers

• LC-GRPO: Bridging Train-Inference Gap for Flow-Based GRPO with Langevin Correction [59.32834240526981]
  Flow-based generative models are typically sampled by solving a deterministic ordinary differential equation (ODE)<n>Existing GRPO methods for flow models replace the Euler-time ODE with aotropic differential equation (SDE) during training.<n>We introduce LC-GRPO, a flow-based GRPO framework with Langevin correction targeting the marginal distribution at the resulting timestep.
  arXiv  Detail & Related papers  (2026-08-06T04:47:57Z)
• Twisted Schrödinger Bridge Matching [34.126987447337534]
  Diffusion-based Schrdinger bridge models have been proposed to approximate optimal transport dynamics between two prescribed boundary distributions.<n>We introduce Twisted Schrdinger Bridge Matching, a diffusion-based method designed to handle both continuous- and discrete-time potentials.
  arXiv  Detail & Related papers  (2026-07-18T22:30:43Z)
• Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions [6.144605787421899]
  Multi-Fidelity Flow Matching is a cascade refinement framework for PDE solutions.<n>We exploit this in Multi-Fidelity Flow Matching (MFFM), a cascade refinement framework for PDE solutions.<n>MFFM is a learned analog of multigrid refinement that reaches the finest grid in $L$ deterministic network evaluations per query.
  arXiv  Detail & Related papers  (2026-05-15T16:02:18Z)
• QDSB: Quantized Diffusion Schrödinger Bridges [4.3331379059769395]
  We propose quantized diffusion Schrdinger bridges (QDSB), which compute the endpoint coupling on anchor-quantized endpoint distributions.<n>We show that the regularized optimal coupling is stable w.r.t. anchor quantization, with an error controlled by the quality of the anchor approximation.
  arXiv  Detail & Related papers  (2026-05-12T11:35:08Z)
• Analytic Bridge Diffusions for Controlled Path Generation [0.0]
  Most modern bridge-diffusion methods achieve finite-time transport by specifying an objective and then learning the associated score or drift field with a neural network.<n>In LQ-GM-PID, we retain the linear-quadratic-control backbone, but replace terminal state regulation by a prescribed terminal probability density.<n>LQ-GM-PID turns bridge diffusion from a tool for terminal target matching alone into a tool for path shaping.
  arXiv  Detail & Related papers  (2026-05-03T05:36:52Z)
• Posterior Augmented Flow Matching [64.1559809786948]
  Posterior-Augmented Flow Matching (PAFM) is a generalization of flow matching (FM)<n>We show that PAFM improves over FM by up to 3.4 FID50K across different model scales.
  arXiv  Detail & Related papers  (2026-05-01T17:59:59Z)
• Riemannian MeanFlow for One-Step Generation on Manifolds [54.09734511705173]
  Flow Matching enables simulation-free training of generative models.<n>MeanFlow can be extended to manifold-valued generation where velocities lie in location-dependent tangent spaces.<n>Experiments on spheres, tori, and SO(3) demonstrate competitive one-step sampling with improved quality-efficiency trade-offs and substantially reduced sampling cost.
  arXiv  Detail & Related papers  (2026-03-11T12:41:46Z)
• RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions [1.7498738677484031]
  Polynomial-based multistep samplers mitigate this cost by accelerating the sampling trajectory according to a predefined scheme.<n>We propose RBF-r, a multistep diffusion sampler that interpolates model evaluations with radial basis functions (RBFs)<n>By leveraging learnable shape parameters in RBFs, RBF-r explicitly follows optimal sampling trajectories.
  arXiv  Detail & Related papers  (2026-03-05T06:19:44Z)
• PINGS: Physics-Informed Neural Network for Fast Generative Sampling [0.0]
  We introduce PINGS, a framework that amortizes diffusion sampling by training a physics-informed network to approximate reverse-time probability-flow dynamics.<n>As a proof of concept, we learn a direct map from a 3D standard normal to a non-Gaussian Gaussian Mixture Model (GMM)<n>PINGS frames generative sampling as a PINN-style residual problem with endpoint anchoring, yielding a white-box, differentiable map with NFE = 1.
  arXiv  Detail & Related papers  (2025-09-14T14:22:33Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network [59.79008107609297]
  We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network. We use a single GFlowNet whose sampling policy follows a two-phase process. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
  arXiv  Detail & Related papers  (2023-05-30T19:16:44Z)

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.