Research map / Optimization / Nonconvex and smooth optimization
Reducing Contextual Stochastic Bilevel Optimization via Structured Function Approximation
Maxime Bouscary, Jiawei Zhang, Saurabh Amin
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 |
|---|---|---|---|
| replace stocBiO partitioning with basis-function reduction | stocBiO · Inverse optimization | N for within 3% gap: N=50 -> N = 5 | Improved |
| use Chebyshev or Fourier basis instead of stocBiO | stocBiO[N] · Inverse optimization | N for smallest loss: N >= 100 -> N >= 10 | Improved |
| use more expressive Chebyshev/Fourier basis instead of monomial | reduction R_Phi · Inverse optimization | lower-level error | Improved |
| use Chebyshev basis N=5 in hyperparameter optimization vs stocBiO | stocBiO[N] · Hyperparameter optimization (MNIST) | validation loss | Improved |
| add more Chebyshev basis functions beyond 5 (ablation) | R_Chebyshev · Hyperparameter optimization (MNIST) | validation loss | No clear effect |
| use larger N in stocBiO (ablation) | stocBiO[N] · Hyperparameter optimization (MNIST) | validation loss | Mixed |
| use monomial instead of Chebyshev basis at large N (ablation) | R_Phi · Hyperparameter optimization (MNIST) | validation loss | Hurt |
Closest papers by meaning
- Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.91)
- Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling (NeurIPS 2024 · similarity 0.91)
- Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems (NeurIPS 2026 · similarity 0.91)
- Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization (NeurIPS 2026 · similarity 0.91)
- On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation (ICLR 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.
