DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity

Zhen Qin, Zhuqing Liu, Songtao Lu, Yingbin Liang, Jia Liu

Keywords: Decentralized optimization, Bilevel optimization, Convex optimization, Heterogeneous data distributions, Multi agent learning

Abstract:

Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion without the need for a central server.
However, most existing DBO methods rely on lower-level strong convexity (LLSC) to guarantee unique solutions and a well-defined hypergradient for stationarity measure, hindering their applicability in many practical scenarios not satisfying LLSC.
To overcome this limitation, we introduce a new single-loop DBO algorithm called diminishing quadratically-regularized bilevel decentralized optimization (DUET), which eliminates the need for LLSC by introducing a diminishing quadratic regularization to the lower-level (LL) objective.
We show that DUET achieves an iteration complexity of $O(1/T^{1-5p-\frac{11}{4}\tau})$ for approximate KKT-stationary point convergence under relaxed assumptions, where $p$ and $\tau $ are control parameters for LL learning rate and averaging, respectively.
In addition, our DUET algorithm incorporates gradient tracking to address data heterogeneity, a key challenge in DBO settings.
To the best of our knowledge, this is the first work to tackle DBO without LLSC under decentralized settings with data heterogeneity.
Numerical experiments validate the theoretical findings and demonstrate the practical effectiveness of our proposed algorithms.

Primary Area: optimization

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 12177