DUET achieves O(1/T^{1-5p-11/4 τ}) iteration complexity for approximate KKT-stationary points in decentralized bilevel optimization without lower-level strong convexity, using gradient tracking for data heterogeneity.
Proceedings of the AAAI Conference on Artificial Intelligence , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
DUET achieves O(1/T^{1-5p-11/4 τ}) iteration complexity for approximate KKT-stationary points in decentralized bilevel optimization without lower-level strong convexity, using gradient tracking for data heterogeneity.