Pith. sign in

REVIEW 10 cited by

Closed-Form Diffusion Models

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 2310.12395 v3 pith:RFX3ZE35 submitted 2023-10-19 cs.LG stat.ML

Closed-Form Diffusion Models

classification cs.LG stat.ML
keywords scoretrainingfunctionclosed-formerrorestimatormodelsneural
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Score-based generative models (SGMs) sample from a target distribution by iteratively transforming noise using the score function of the perturbed target. For any finite training set, this score function can be evaluated in closed form, but the resulting SGM memorizes its training data and does not generate novel samples. In practice, one approximates the score by training a neural network via score-matching. The error in this approximation promotes generalization, but neural SGMs are costly to train and sample, and the effective regularization this error provides is not well-understood theoretically. In this work, we instead explicitly smooth the closed-form score to obtain an SGM that generates novel samples without training. We analyze our model and propose an efficient nearest-neighbor-based estimator of its score function. Using this estimator, our method achieves competitive sampling times while running on consumer-grade CPUs.

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. An exact information theory of generalization phase transitions in Bayesian diffusion models

    cs.LG 2026-07 conditional novelty 8.0

    Bayesian diffusion models memorize training data when mutual information between restricted observations and training data exceeds log dataset size, and generalize otherwise.

  2. Bayesian Experimental Design via Score Matching

    stat.ML 2026-07 conditional novelty 7.0

    SCOREBED isolates EIG double intractability in a policy-independent score-matching stage, then trains design policies with a singly intractable gradient estimator, enabling cheap multi-policy selection.

  3. Training-Free Generative Sampling via Moment-Matched Score Smoothing

    stat.ML 2026-05 unverdicted novelty 7.0

    MM-SOLD is a training-free particle sampler whose large-particle limit converges to a moment-matched Gibbs distribution obtained by exponentially tilting a score-smoothed target.

  4. Is Flow Matching Just Trajectory Replay for Sequential Data?

    stat.ML 2026-02 unverdicted novelty 7.0

    Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented...

  5. On The Hidden Biases of Flow Matching Samplers

    stat.ML 2025-12 unverdicted novelty 7.0

    Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlli...

  6. Substitution-Based Analysis of Structural Novelty for Generative Models of Materials

    cs.LG 2026-06 unverdicted novelty 6.0

    81-92% of chemically valid and metastable crystals from generative models are training duplicates or substitution-derived, with low-symmetry cases showing interpolation and high-symmetry cases showing memorization.

  7. Path convergence in diffusion models

    cond-mat.stat-mech 2026-06 unverdicted novelty 6.0

    In a 1D test case, backward diffusion paths converge to the infinite-pattern limit on a 1/sqrt(p) scale with infinite mean square deviation, enabling an extrapolation algorithm for density estimation and generalization.

  8. The two clocks and the innovation window: When and how generative models learn rules

    cs.LG 2026-05 unverdicted novelty 6.0

    Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.

  9. Diffusion Models Memorize in Training -- and Generalize in Inference

    cs.LG 2026-03 unverdicted novelty 6.0

    Diffusion models overfit denoising loss at intermediate noise but generalize in inference as model error smooths the flow field and sampling paths avoid memorized noisy training data.

  10. Demystifying Transition Matching: When and Why It Can Beat Flow Matching

    cs.LG 2025-10 unverdicted novelty 6.0

    TM outperforms FM for well-separated modes with non-negligible variance by preserving covariance via stochastic latent updates, with the gap closing as variance approaches zero.