Research map / Optimization / Nonconvex and smooth optimization
An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition
Quan Xiao, Songtao Lu, Tianyi Chen
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 |
|---|---|---|---|
| Use GALET instead of BOME for bilevel hyper-cleaning | bilevel optimization · Hyper-cleaning on MNIST | test accuracy: 88.20 -> 90.20 | Improved |
| Use GALET instead of V-PBGD | bilevel optimization · Hyper-cleaning on MNIST | test accuracy: 90.24 -> 90.20 | No clear effect |
| Use GALET instead of IAPTT-GM | bilevel optimization · Hyper-cleaning on MNIST | test accuracy: 90.13 -> 90.20 | No clear effect |
| Vary upper-level stepsize alpha in {0.1,0.3,0.5,0.7,0.9} (ablation) | GALET · Example 1 trajectories | trajectory / optimality gap | Mixed |
| Vary shadow implicit gradient loops T in {1,5,50} and stepsize gamma in {0.1,0.5} (ablation) | GALET · Example 1 trajectories | trajectory | No clear effect |
| Vary lower-level loops N in {1,5} and stepsize beta in {0.1,0.5,1,3} (ablation) | GALET · Example 1 trajectories | trajectory | No clear effect |
| Use the proposed stationary measure instead of value-function KKT score | GALET · Example 1 | convergence to 0 | Improved |
Closest papers by meaning
- An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization (NeurIPS 2024 · similarity 0.92)
- On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.91)
- TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization (ICML 2025 · similarity 0.91)
- Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization (ICML 2024 · similarity 0.91)
- Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds (NeurIPS 2024 · similarity 0.90)
- Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems (NeurIPS 2026 · similarity 0.90)
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.
