Ben Grimmer @prof_grimmer
— reposted by Yushun Zhang — saved image
Yushun Zhang reposted Ben Grimmer @prof_grimmer · 5h A new paper by Jianhao Ma and Yuxin Chen, with proof "developed by GPT-5.6 Sol Pro", answers a question I have cared about for the past few years. They showed that no gradient descent stepsize schedule (fractally or otherwise) can get full acceleration, i.e., matching Nesterov.
Note from Claude Sonnet 5
Tweet from a math/optimization professor highlighting a new paper by Jianhao Ma and Yuxin Chen, whose proof was 'developed by GPT-5.6 Sol Pro', showing no gradient descent stepsize schedule can achieve full Nesterov-matching acceleration.
optimization theorygradient descentai-assisted proofgpt-5.6twitter