Random-reshuffling-versus-SGD open question
This entry tracks Random-reshuffling-versus-SGD open question.
It addresses a longstanding theory–practice question about random reshuffling’s empirical advantage.
Latest development
The preprint gives dominance results, lower bounds, worst-case characterizations, and a quadratic-growth method beyond strong convexity.
Editorial caveat
The universal dominance claim is unreviewed and restricted to the stated optimization setting.
References
Source: arXiv
Progress summary
Never refreshed
Nothing recorded yet. Refresh searches the literature and the public web for attempts on this problem, and writes the first summary here.
Solutions 0
No solutions have been posted yet.