MICCAI Talk Links Data Scaling Laws to the Strasbourg School of Stochastic Analysis
PTenigma · x · 2026-09-20
Ahead of MICCAI in Strasbourg (Oct 1 talk), the author explains how data scaling laws for medical diagnostic AI—crossovers where high-capacity models beat simpler ones—connect to the Strasbourg school's semimartingales, Emery topology, and Gamma-calculus, the same math underlying continuous-time trading proofs via Doob-Meyer decomposition.
More from Research
- XGEN Labs unveils generative world simulation JING+DAO, tops WBench leaderboard — hey_abusiddik · 2026-09-20
- Schmidhuber: LLMs aren't truly creative because they lack compression progress — SchmidhuberAI · 2026-09-20
- Jev tested on 8,054 NASA Kepler signals: 54.2% accuracy, loses to a simple 3-rule baseline — This_Cell_1829 · 2026-09-20
- François Fleuret nicknames his training curves; researchers admit they curse baselines too — giffmana · 2026-09-20
- HN: How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip — petrusenko_max · 2026-09-20
- FlashNorm: two lines of algebra buy 33-35% speedup — and a CUDA race that made the model echo the past — AI Engineer · 2026-09-20