On local entropy, stochastic control and deep neural networks
Not on the map. Why?
Abstract (arXiv)
In this paper, we connect some recent papers on smoothing of energy landscapes and scored-based generative models of machine learning to classical work in stochastic control. We clarify these connections providing rigorous statements and representations which may serve as guidelines for further learning models.
Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2022.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 1; 2026: 1.
7 papers.
- 2022An optimal control perspective on diffusion-based generative modelingcited by 145
- 2023Improved sampling via learned diffusionscited by 103
- 2024Stochastic Localization via Iterative Posterior Samplingcited by 27
- 2025Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inferencecited by 22
- 2024Learned Reference-based Diffusion Sampling for multi-modal distributionscited by 9
- 2023Generative Diffusion From An Action Principlecited by 5
- 2026A Stabilized Path-Space Approach to Diffusion-Based Posterior Samplingcited by 1
- 2026A Stabilized Path-Space Approach to Diffusion-Based Posterior Sampling10 Jun 2026
- 2025Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference17 Aug 2025
- 2024Learned Reference-based Diffusion Sampling for multi-modal distributions25 Oct 2024
- 2024Stochastic Localization via Iterative Posterior Sampling16 Feb 2024
- 2023Generative Diffusion From An Action Principle6 Oct 2023
- 2023Improved sampling via learned diffusions3 Jul 2023
- 2022An optimal control perspective on diffusion-based generative modeling2 Nov 2022