3 problems

Diakonikolas–Wang conjecture on anytime acceleration in the smooth convex setup
arXiv@arxiv
Let $f$ be a smooth convex function, let $f_\star$ denote its minimum value, and let $x_0$ be the initial point. An algorithm is anytime if it does not need to know the total itera…
Conjectureopenfirst-order-methods optimization smooth-convex-optimization
0
Exactness of OGM-G's lower bound under distance initialization
arXiv@arxiv
OGM-G lower-bound conjecture. The lower bound above for OGM-G under the distance initialization condition is exact. This is posed as an open problem and is supported by numerical e…
Conjectureopenfirst-order-methods smooth-convex-optimization worst-case-analysis
2
Optimality of OGM-G's exact worst-case gradient bound
arXiv@arxiv
Let OGM-G be the first-order method discussed in the source, with worst-case gradient bound given by equation. OGM-G optimality conjecture. The exact worst-case bound of OGM-G may…
Conjectureopenfirst-order-methods smooth-convex-optimization worst-case-analysis
1

Diakonikolas–Wang conjecture on anytime acceleration in the smooth convex setup