# DDPM Score Matching and Distribution Learning

arXiv: https://arxiv.org/abs/2504.05161 · HTML: https://mlsanity.com/paper/2504.05161/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 4 of its 242 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 4 of 4)

- [Robustly Learning any Clusterable Mixture of Gaussians](https://mlsanity.com/paper/2005.06417/) (2020)
- [Outlier-Robust Clustering of Non-Spherical Mixtures](https://mlsanity.com/paper/2005.02970/) (2020)
- [A Score-Based Density Formula, with Applications in Diffusion Generative Models](https://mlsanity.com/paper/2408.16765/) (2024)
- [Nonparametric MLE for Gaussian Location Mixtures: Certified Computation and Generic Behavior](https://mlsanity.com/paper/2503.20193/) (2025)

## Built on by (most cited first, 7 of 7)

- [Feedback Guidance of Diffusion Models](https://mlsanity.com/paper/2506.06085/) (2025)
- [Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling Guarantees](https://mlsanity.com/paper/2601.06715/) (2026)
- [Quantifying Epistemic Uncertainty in Diffusion Models](https://mlsanity.com/paper/2602.09170/) (2026)
- [Complexity of Non-Log-Concave Sampling in Fisher Information](https://mlsanity.com/paper/2605.15859/) (2026)
- [A computational phase transition for learning-to-sample from Ising models](https://mlsanity.com/paper/2605.24752/) (2026)
- [Connecting Score Matching, Maximum Likelihood, and Expectation-Maximization in Mixed Linear Regression](https://mlsanity.com/paper/2609.05688/) (2026)
- [Robustness of Diffusion Models under Distribution Shift](https://mlsanity.com/paper/2609.27546/) (2026)

## Abstract (arXiv)

Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key result in this area shows that with accurate score estimates, SGMs can efficiently generate samples from any realistic data distribution (Chen et al., ICLR'23; Lee et al., ALT'23). This distribution learning result, where the learned distribution is implicitly that of the sampler's output, does not explain how score estimation relates to classical tasks of parameter and density estimation. This paper introduces a framework that reduces score estimation to these two tasks, with various implications for statistical and computational learning theory: Parameter Estimation: Koehler et al. (ICLR'23) demonstrate that a score-matching variant is statistically inefficient for the parametric estimation of multimodal densities common in practice. In contrast, we show that under mild conditions, denoising score-matching in DDPMs is asymptotically efficient. Density Estimation: By linking generation to score estimation, we lift existing score estimation guarantees to (ε,δ)-PAC density estimation, i.e., a function approximating the target log-density within ε on all but a δ-fraction of the space. We provide (i) minimax rates for density estimation over H"older classes and (ii) a quasi-polynomial PAC density estimation algorithm for the classical Gaussian location mixture model, building on and addressing an open problem from Gatmiry et al. (COLT'26). Lower Bounds for Score Estimation: Our framework offers the first principled method to prove computational lower bounds for score estimation across general distributions. As an application, we establish cryptographic lower bounds for score estimation in general Gaussian mixture models, conceptually recovering Song's (NeurIPS'24) result and advancing his key open problem.