AI-assisted proof: first high-probability regret bounds for Feel-good Thompson sampling
QuanquanGu · x · 2026-10-31
Quanquan Gu's group shares how AI helped their new paper proving the first high-probability regret bounds (Õ(d√T)) for Feel-good Thompson sampling in linear contextual bandits. Their initial UCB-style idea was deemed unnecessary by the AI, which showed Markov's inequality solves it cleanly — though understanding the AI's key technical steps was hard. The team is now working on automating the understanding and presentation of AI-generated math.
More from Research
- Zip-NeRF Gets Orders of Magnitude Faster to Train, but Rendering Still Crawls at 3-4 FPS — jonstephens85 · 2026-10-31
- Researchers reconstruct Meta Muse's hidden charter from 884 chain-of-thought samples — sethlazar · 2026-10-31
- 14 AI models tested on 8,000 startups: none beats simply ranking by hiring growth — HeyAmit_ · 2026-10-31
- Working Paper Argues AI Can Break the Coasian Ceiling on Firm Size — zetalyrae · 2026-10-31
- Molence Bio Open-Sources Mol-1, Matching Closed SOTA at Antibody Structure Prediction — AllThingsApx · 2026-10-31
- Revisiting why transformers can't do zero-shot recursion, via Transformer Circuits math — akbirthko · 2026-10-31