PF-AGD is the first parameter-free deterministic accelerated first-order method with Õ(ε^{-5/3} log(1/ε)) complexity for smooth non-convex optimization.
Restarted nonconvex accelerated gradient descent: No more polylogarithmic factor in the O(ϵ−7/4) complexity.Journal of Machine Learning Research, 24 (157):1–37
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Parameter-Free First-Order Algorithm for Non-Convex Optimization with $\tilde{\mkern1mu O}(\epsilon^{-5/3})$ Global Rate
PF-AGD is the first parameter-free deterministic accelerated first-order method with Õ(ε^{-5/3} log(1/ε)) complexity for smooth non-convex optimization.