Exhaustive AdaBoost Cycling Question
Does exhaustive AdaBoost always converge to a finite cycle of weak classifiers and weight vectors on every finite training set? A finite instance whose orbit never becomes periodic answers no.
- Result
- Disproved
- Status
- Resolved
- AI contribution
- AI co-developed
- Method
- Construction
- Field
- Learning theory
- Posed by
- Cynthia Rudin, Robert Schapire & Ingrid Daubechies
- Year posed
- 2012
- Years open
- 14y
- Solved
- 2026-04-08
- Model
- GPT-5.4 Pro, Claude Opus 4.6
- Vendor
- OpenAI / Anthropic
- Collaborators
- —
- Verification
- Unreviewed
- Publication
- Preprint
- Significance
- 15 / 100
- Disclosed cost
- —
- Wikipedia
- No dedicated article
What the AI did
The block-product gadget - two factors sharing an exact period-2 orbit whose linearized return maps have dominant eigenvalues with an irrational logarithmic ratio - was developed with GPT-5.4 Pro and Claude Opus 4.6.
Verification
All assertions certified by exact rational arithmetic; computer-assisted arXiv preprint, not yet peer-reviewed.