Research map / Optimization / Optimizers
A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 FSLA instead of BP for data hyper-cleaning | Bilevel optimization with a 4-layer CNN · MNIST data hyper-cleaning | validation loss | Helped |
| Use FSLA instead of CG for data hyper-cleaning | Bilevel optimization with a 4-layer CNN · Fashion-MNIST and QMNIST data hyper-cleaning | validation loss | Helped |
| Track and reuse historical hyper-gradient information rather than recomputing it (ablation) | FSLA versus CG_1_1 · MNIST data hyper-cleaning | validation loss | Helped |
| Add the warm-start strategy for inner updates (ablation) | Single-loop NS and CG · Data hyper-cleaning | validation loss | Helped |
| Use FSLA instead of BP, NS, or CG for hyper-gradient estimation | Synthetic quadratic objective · Synthetic quadratic objective | hyper-gradient estimation error | Mixed |
| Use CG rather than NS to approximate the hyper-gradient | Hyper-gradient estimation · Synthetic quadratic objective | iterations to reach a given estimation error | Helped |
Closest papers by meaning
- A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization (NeurIPS 2025 · similarity 0.92)
- Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis (ICLR 2025 · similarity 0.91)
- A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation (NeurIPS 2025 · similarity 0.90)
- Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling (NeurIPS 2024 · similarity 0.90)
- Double Momentum Method for Lower-Level Constrained Bilevel Optimization (ICML 2024 · similarity 0.90)
- A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness (ICML 2024 · 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.