Helmholtz-SDE: simulation-free VI for latent SDEs matches SBI at a fraction of the runtime
canaesseth · x · 2026-10-06
A paper by @smithhenryd, @brianltrippe and @scottlinderman, Helmholtz-SDE studies analytic approximations for latent SDEs. The key result: simulation-free variational inference for latent SDEs can match the performance of simulation-based VI at a fraction of the runtime, offering a major speedup for such models.
More from Research
- The old route to math advances via conjecture-gathering will soon matter less, author argues — _onionesque · 2026-10-07
- Math as a strip mine: why AI can exploit decades of pre-mapped intermediate results — _onionesque · 2026-10-07
- RaiSim is back: v2.8.0 brings ultra-fast accurate CPU simulation plus photorealistic rendering — ChongZzZhang · 2026-10-07
- DAEDALUS bootstraps agent memory from self-generated tasks, +15.9 points success rate — illuin · 2026-10-07
- Storing model-native numerical memory outside a frozen LLM: replicated from Qwen to Mistral, 127/128 Top-1 — Nearby_Indication474 · 2026-10-07
- Mathematicians release skill files to de-slop LLM-written math papers — IAmTimNguyen · 2026-10-07