Research map / Optimization / Nonconvex and smooth optimization
Contextual Stochastic Bilevel Optimization
Yifan Hu, Jie Wang, Yao Xie, Andreas Krause, Daniel Kuhn
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 RT-MLMC instead of DL-SGD gradient estimator at K=12 | bilevel gradient estimator · Meta-learning tinyImageNet | computation time (mean): 9.38e-01 -> 1.08e-01 | Improved |
| use RT-MLMC instead of DL-SGD at K=6 | bilevel gradient estimator · Meta-learning tinyImageNet | computation time (mean): 2.65e-02 -> 2.73e-02 | No clear effect |
| use RT-MLMC instead of DL-SGD at K=8 | bilevel gradient estimator · WDRO-SI newsvendor | computation time (mean): 4.63e-01 -> 3.41e-02 | Improved |
| use RT-MLMC instead of DL-SGD at K=2 | bilevel gradient estimator · WDRO-SI newsvendor | computation time (mean): 1.27e-02 -> 5.04e-03 | Improved |
| increase lower-level accuracy K | DL-SGD and RT-MLMC · Meta-learning tinyImageNet | test error | Improved |
| increase lower-level epochs K | DL-SGD and RT-MLMC · WDRO-SI newsvendor | test loss | Improved |
| replace one-step MAML with RT-MLMC | meta-learning · tinyImageNet | test error | Improved |
| use m-step MAML (m in 1,4,8,12) instead of one-step (ablation) | MAML · tinyImageNet | test error | Improved |
| increase MAML inner stepsize (ablation) | MAML · tinyImageNet | test error | Hurt |
| use RT-MLMC instead of BSVRB v2 at equal epochs | meta-learning · tinyImageNet | test error | Improved |
| incorporate side information (WDRO-SI) vs ERM and WDRO | newsvendor · WDRO-SI | test loss | Improved |
| generate more samples m of eta per side information | WDRO-SI · newsvendor | test loss | Improved |
Closest papers by meaning
- A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness (ICML 2024 · similarity 0.91)
- SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity (ICML 2024 · similarity 0.90)
- An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness (NeurIPS 2024 · similarity 0.89)
- TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization (ICML 2025 · similarity 0.89)
- Double Momentum Method for Lower-Level Constrained Bilevel Optimization (ICML 2024 · similarity 0.89)
- Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.88)
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.
