Data Generation without Function Estimation
Not on the map. Why?
Abstract (arXiv)
Estimating the score function (or other population-density-dependent functions) is a fundamental component of most generative models. However, such function estimation is computationally and statistically challenging. Can we avoid function estimation for data generation? We propose an estimation-free generative method: A set of points whose locations are deterministically updated with (inverse) gradient descent can transport a uniform distribution to arbitrary data distribution, in the mean field regime, without function estimation, training neural networks, and even noise injection. The proposed method is built upon recent advances in the physics of interacting particles. We show, both theoretically and experimentally, that these advances can be leveraged to develop novel generative methods.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 11 Jul 2025.
Builds on
23 of 48 references.
References · 23
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2015Variational Inference with Normalizing Flowscited by 2,170
- 2018On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transportcited by 426
- 2016Input Convex Neural Networkscited by 414
- 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 206
- 2019Maximum Mean Discrepancy Gradient Flowcited by 127
- 2022Poisson Flow Generative Modelscited by 95
- 2021Proximal Optimal Transport Modeling of Population Dynamicscited by 93
- 2021Large-Scale Wasserstein Gradient Flowscited by 77
11 more
- 2023PFGM++: Unlocking the Potential of Physics-Inspired Generative Modelscited by 73
- 2024Optimal score estimation via empirical Bayes smoothingcited by 61
- 2021Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networkscited by 53
- 2021Variational Wasserstein gradient flowcited by 53
- 2017Stochastic Particle Gradient Descent for Infinite Ensemblescited by 52
- 2021Efficient Gradient Flows in Sliced-Wasserstein Spacecited by 21
- 2021Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimizationcited by 6
- 2025Field Matching: an Electrostatic Paradigm to Generate and Transfer Datacited by 6
- 2023Efficient displacement convex optimization with particle gradient descentcited by 5
- 2023Minimizers for an aggregation model with attractive-repulsive interactioncited by 3
- 2024Cryptographic Hardness of Score Estimationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.