New Papers Extend Simulation-Free Neural SDE Learning Beyond One-Time Marginals
A series of new papers extends SDE Matching to continuous physical time, enabling simulation-free learning of temporal structure beyond one-time marginals. Notably, the Helmholtz-SDE work closes the approximation gap in simulation-free latent SDEs, greatly speeding up inference.
2026-10-06 ~ 2026-10-06 · 4 related posts
- Gaussian Flow Dynamics enables simulation-free neural SDEs learning temporal structure — canaesseth · 2026-10-06
- Helmholtz-SDE closes the approximation gap in simulation-free latent SDE inference — canaesseth · 2026-10-06
- SDE Matching extended beyond one-time marginals to learn generative models in physical time — canaesseth · 2026-10-06
- Helmholtz-SDE: simulation-free VI for latent SDEs matches SBI at a fraction of the runtime — canaesseth · 2026-10-06