Dietterich clarifies: symbolic regression solves it, he cares about neural nets
tdietterich · x · 2026-10-11
Following up on his question about whether LLMs can recover x = ½at² from (x,t) pairs of constant-acceleration motion, Thomas Dietterich clarifies that symbolic regression methods already accomplish this — his real interest is whether neural networks and LLMs can generalize this way, or are merely doing kernel interpolation. The follow-up sharpens the gap between deep learning's function approximation and true law discovery.
Related event: Dietterich and LeCun Debate Whether LLMs Generalize or Just Interpolate(3 posts)→
More from Research
- Lab automation only handles cookie-cutter assays — the long tail is what stifles innovation — anshulkundaje · 2026-10-11
- ArXiv caps submissions at two per month as AI paper flood overwhelms server — The Decoder · 2026-10-11
- Warning: engram/n-gram methods may markedly amplify overfitting under data repeat — SonglinYang4 · 2026-10-11
- MIT's FleXray segments 60 anatomical structures in any X-ray, runs in-browser — Dr_Alex_Crimi · 2026-10-11
- OpenAI's math formalization push called 'greatest gift to mathematics' — basedjensen · 2026-10-11
- Numerical-memory method validated on DeepSeek-V2-Lite: 2.58 MiB, 69/72 correct — Nearby_Indication474 · 2026-10-11