Grant Rotskoff
@grant.rotskoff.cc
Statistical mechanic working on generative models for biophysics and beyond. Assistant professor at Stanford. https://statmech.stanford.edu
Jérémie Klinger found a simple trick back to Girsanov: you take the perturbation in the diffusion at the level of the Fokker-Planck equation and rewrite it to be included in the drift. The resulting drift then has a term proportional to \nabla \log \rho(x,t), what machine learners call the score!
March 4, 2025 at 6:45 PM
Jérémie Klinger found a simple trick back to Girsanov: you take the perturbation in the diffusion at the level of the Fokker-Planck equation and rewrite it to be included in the drift. The resulting drift then has a term proportional to \nabla \log \rho(x,t), what machine learners call the score!
Excited to see our paper “Computing Nonequilibrium Responses with Score-Shifted Stochastic Differential Equations” in Physical Review Letters this morning as an Editor’s Suggestion! We uses ideas from generative modeling to unravel a rather technical problem. 🧵 journals.aps.org/prl/abstract...
March 4, 2025 at 6:45 PM
Excited to see our paper “Computing Nonequilibrium Responses with Score-Shifted Stochastic Differential Equations” in Physical Review Letters this morning as an Editor’s Suggestion! We uses ideas from generative modeling to unravel a rather technical problem. 🧵 journals.aps.org/prl/abstract...
If you didn't see our poster at NeurIPS on how to make diffusion model inference fast, you can always read the paper here: arxiv.org/abs/2405.15986
December 13, 2024 at 4:22 PM
If you didn't see our poster at NeurIPS on how to make diffusion model inference fast, you can always read the paper here: arxiv.org/abs/2405.15986