Research map / Optimization / Nonconvex and smooth optimization
Convergence Analysis of Decentralized Hessian-/Jacobian-Free Algorithm for Nonconvex Stochastic Bilevel Optimization
Yihan Zhang, Xinwen Zhang, My T. Thai, Jie Wu, Hongchang Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase the learning rate eta (ablation) | proposed decentralized first-order bilevel algorithm · hyperparameter optimization on a9a | upper-level loss convergence | Mixed |
| vary the momentum coefficient (ablation) | proposed decentralized first-order bilevel algorithm · hyperparameter optimization on a9a | upper-level loss convergence | No clear effect |
| use a smaller penalty parameter rho (larger penalty 1/rho) (ablation) | proposed decentralized first-order bilevel algorithm · hyperparameter optimization on a9a | upper-level loss convergence | Improved |
| use the proposed algorithm instead of F2BSA variants (F2BSA-1, -5, -10, -VR) | decentralized bilevel optimization · hyperparameter optimization (a9a, w8a, covtype, MNIST) | upper-level loss vs iterations | Improved |
| use the proposed algorithm instead of F2BSA variants | decentralized bilevel optimization · model pruning ResNet20 CIFAR10 (20% parameters kept) | upper-level loss vs iterations | Improved |
| use the fully first-order algorithm instead of second-order DSBO, gossip-DSBO, MA-DSBO, VRDBO, DSVRBGD-S | strongly convex lower-level hyperparameter optimization · logistic regression hyperparameter optimization | time to convergence | Improved |
| add variance-reduced gradients relative to DSFDA-GT | fully first-order decentralized bilevel method · logistic regression hyperparameter optimization | convergence | Improved |
Closest papers by meaning
- Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise (NeurIPS 2026 · similarity 0.93)
- Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization (ICML 2024 · similarity 0.91)
- TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization (ICML 2025 · similarity 0.90)
- DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity (ICLR 2025 · similarity 0.89)
- Problem-Parameter-Free Decentralized Bilevel Optimization (NeurIPS 2025 · similarity 0.89)
- Locally Differentially Private Decentralized Stochastic Bilevel Optimization with Guaranteed Convergence Accuracy (ICML 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
