Research map / Optimization / Nonconvex and smooth optimization
Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem
Jincheng Cao, Ruichen Jiang, Nazanin Abolfazli, Erfan Yazdandoost Hamedani, Aryan Mokhtari
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 SBCGF (finite-sum, sqrt(n) samples per iteration, constant step) instead of aR-IP-SeG | Bilevel sparse regression · Wikipedia Math Essential, over-parameterized regression | lower- and upper-level gap | Improved |
| use SBCGI (one sample per iteration) instead of aR-IP-SeG | Bilevel sparse regression · Wikipedia Math Essential | lower- and upper-level gap | Improved |
| use DBGD-sto instead of the proposed methods | Bilevel sparse regression · Wikipedia Math Essential | lower-level error | Hurt |
| compare test error of SBCGF, SBCGI, DBGD-sto against aR-IP-SeG | Bilevel sparse regression · Wikipedia Math Essential | test error | Improved |
| SBCGI with single-sample decreasing step-size versus SBCGF with sqrt(n) samples and constant step | Bilevel sparse regression · Wikipedia Math Essential | stability of performance criteria | Hurt |
| use SBCGF instead of other methods on non-convex upper-level dictionary learning | Dictionary learning bilevel · Synthetic dictionary learning | lower-level objective | Improved |
| use SBCGI, SBCGF or DBGD-sto instead of aR-IP-SeG | Dictionary learning bilevel · Synthetic dictionary learning | upper-level objective and recovery rate | Improved |
Closest papers by meaning
- Conditional Gradient Methods with Standard LMO for Stochastic Simple Bilevel Optimization (NeurIPS 2025 · similarity 0.94)
- Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems (NeurIPS 2026 · similarity 0.93)
- An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization (NeurIPS 2024 · similarity 0.93)
- On The Complexity of First-Order Methods in Stochastic Bilevel Optimization (ICML 2024 · similarity 0.92)
- On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation (ICLR 2024 · similarity 0.92)
- Stochastic Dynamic Barrier Perturbed Gradient Methods for Nonconvex Simple Bilevel Optimization (NeurIPS 2026 · similarity 0.92)
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.
