MELMO provably matches the best known convergence rates for weakly convex composite optimization while allowing non-Euclidean update directions.
In: International Conference on Machine Learning, pp
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
-
Variable Smoothing for Weakly Convex Problems with Non-Euclidean Directions
MELMO provably matches the best known convergence rates for weakly convex composite optimization while allowing non-Euclidean update directions.