Research map / Optimization / Nonconvex and smooth optimization
A framework for bilevel optimization that enables stochastic and global variance reduction algorithms
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 |
|---|---|---|---|
| add SAGA-style global variance reduction (SABA) instead of plain stochastic directions (SOBA) | SOBA · IJCNN1 hyperparameter selection | suboptimality gap h(x)-h* | Helped |
| use SABA instead of competing stochastic bilevel methods (stocBiO, AmIGO, FSLA, MRBO, TTSA, BSA, SUSTAIN) | SABA · MNIST data hyper-cleaning (p=0.5) | test error | Helped |
| use SOBA instead of stocBiO and BSA | SOBA · MNIST data hyper-cleaning (p=0.5) | final test error | Helped |
| use SOBA instead of TTSA and FSLA | SOBA · IJCNN1 hyperparameter selection | suboptimality gap | No clear effect |
Closest papers by meaning
- A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness (ICML 2024 · similarity 0.91)
- An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness (NeurIPS 2024 · similarity 0.90)
- SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity (ICML 2024 · similarity 0.90)
- Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.90)
- TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization (ICML 2025 · similarity 0.89)
- Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis (ICLR 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.