PAGE is shown to converge for weakly convex finite-sum problems with rates interpolating between nonconvex and convex cases, improving the known convex-case complexity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convergence Analysis of the ProbAbilistic Gradient Estimator Algorithm for Weakly Convex Finite-Sum Optimization
PAGE is shown to converge for weakly convex finite-sum problems with rates interpolating between nonconvex and convex cases, improving the known convex-case complexity.