Pith. sign in

REVIEW 10 cited by

Diffusion Schr\"odinger Bridge with Applications to Score-Based Generative Modeling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.01357 v5 pith:WU7HBQ5K submitted 2021-06-01 stat.ML cs.LGmath.PR

Diffusion Schr\"odinger Bridge with Applications to Score-Based Generative Modeling

classification stat.ML cs.LGmath.PR
keywords generativetimedatadistributiongaussianmodelingproblemapproximately
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Progressively applying Gaussian noise transforms complex data distributions to approximately Gaussian. Reversing this dynamic defines a generative model. When the forward noising process is given by a Stochastic Differential Equation (SDE), Song et al. (2021) demonstrate how the time inhomogeneous drift of the associated reverse-time SDE may be estimated using score-matching. A limitation of this approach is that the forward-time SDE must be run for a sufficiently long time for the final distribution to be approximately Gaussian. In contrast, solving the Schr\"odinger Bridge problem (SB), i.e. an entropy-regularized optimal transport problem on path spaces, yields diffusions which generate samples from the data distribution in finite time. We present Diffusion SB (DSB), an original approximation of the Iterative Proportional Fitting (IPF) procedure to solve the SB problem, and provide theoretical analysis along with generative modeling experiments. The first DSB iteration recovers the methodology proposed by Song et al. (2021), with the flexibility of using shorter time intervals, as subsequent DSB iterations reduce the discrepancy between the final-time marginal of the forward (resp. backward) SDE with respect to the prior (resp. data) distribution. Beyond generative modeling, DSB offers a widely applicable computational optimal transport tool as the continuous state-space analogue of the popular Sinkhorn algorithm (Cuturi, 2013).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. One-Step Generative Modeling via Wasserstein Gradient Flows

    cs.LG 2026-05 conditional novelty 7.0

    W-Flow achieves state-of-the-art one-step ImageNet 256x256 generation at 1.29 FID by training a static neural network to follow a Wasserstein gradient flow that minimizes Sinkhorn divergence, delivering roughly 100x f...

  2. The Diffusion-Attention Connection

    cs.LG 2026-02 unverdicted novelty 7.0

    Attention, diffusion maps, and magnetic Laplacians are different regimes of a single Markov geometry from pre-softmax query-scores, linked by a QK bidivergence and Schrödinger bridges into equilibrium, nonequilibrium,...

  3. Spectral Diffusion for Protein Dynamics

    q-bio.BM 2026-07 conditional novelty 6.5

    Diffusion over DCT spectral volumes of Cα displacements yields fast, temperature-conditioned protein trajectories with RMSF Pearson r of 0.844 on held-out mdCATH.

  4. Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation

    cs.RO 2026-06 unverdicted novelty 6.0

    Chronos elevates full observation history to the policy's latent state via selective SSM tokens and a Schrödinger-inspired acceleration bridge, achieving large gains on memory-dependent robot tasks with fewer parameters.

  5. One-Step Generative Modeling via Wasserstein Gradient Flows

    cs.LG 2026-05 unverdicted novelty 6.0

    W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.

  6. Stability of the Monge Map in Semi-Dual Optimal Transport

    math.OC 2026-05 unverdicted novelty 6.0

    Semi-dual optimal transport has a degenerate saddle-point structure equivalent to constrained optimization, with necessary and sufficient conditions derived for Monge map convergence independent of dual potential optimality.

  7. The Ensemble Schr{\"o}dinger Bridge filter for Nonlinear Data Assimilation

    cs.LG 2025-12 unverdicted novelty 6.0

    The Ensemble Schrödinger Bridge filter adds a diffusion-based analysis step to ensemble prediction, enabling effective nonlinear data assimilation without structural model error or training.

  8. Stability of the Monge Map in Semi-Dual Optimal Transport

    math.OC 2026-05 unverdicted novelty 5.0

    Semi-dual OT formulation has degenerate saddle-point structure; necessary and sufficient conditions for Monge map convergence are derived without requiring dual potential optimality.

  9. Stability of the Monge Map in Semi-Dual Optimal Transport

    math.OC 2026-05 unverdicted novelty 5.0

    Semi-dual optimal transport has a degenerate saddle-point structure whose solution is a constrained optimization problem, giving necessary and sufficient conditions for Monge map convergence independent of dual optimality.

  10. A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios

    cs.LG 2025-12 accept novelty 2.0

    A synthesis of diffusion-based simulation-based inference methods that address model misspecification, irregular observations, and missing data in scientific applications.