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.
First-order penalty methods for bilevel optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A deterministic single-loop cubic regularized Newton method for NCSC bilevel optimization that attains the optimal O(ε^{-1.5}) SOSP rate without repeated lower-level solves.
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.
-
On Second-Order Methods for Bilevel Optimization
A deterministic single-loop cubic regularized Newton method for NCSC bilevel optimization that attains the optimal O(ε^{-1.5}) SOSP rate without repeated lower-level solves.