The Yun-Sra-Jadbabaie SS-RS-GD Inequalities
Yun, Sra and Jadbabaie posed as a COLT 2021 open question whether, for well-conditioned symmetric matrices, the operators encoding the expected iterate of single-shuffle SGD, random-reshuffle SGD and gradient descent on a quadratic finite sum satisfy . They do.
- Result
- Proved
- Status
- Resolved
- AI contribution
- AI-discovered
- Method
- Argument
- Field
- Optimization
- Posed by
- Chulhee Yun, Suvrit Sra, Ali Jadbabaie
- Year posed
- 2021
- Years open
- 5y
- Solved
- 2026-06-16
- Model
- GPT-5.5 Pro (extended)
- Vendor
- OpenAI
- Collaborators
- Binghui Peng
- Verification
- Unreviewed
- Publication
- Preprint
- Significance
- 15 / 100
- Disclosed cost
- —
- Wikipedia
- No dedicated article
What the AI did
The paper states the proof was found via GPT-5.5 Pro prompted by the author, and a footnote says the proof idea was completely generated by the model, linking the shared conversation. The write-up was assembled by the author.
Verification
Single-author arXiv preprint with the originating conversation linked; not yet peer-reviewed.
Source
arXiv:2607.22620 - A Resolution of the SS-RS-GD Inequalities