Research map / Optimization / Optimizers
GloptiNets: Scalable Non-Convex Optimization with Certificates
Gaspard Beugnot, Julien Mairal, Alessandro Rudi
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 GN-big instead of GN-small (ablation) | GloptiNets · Random trigonometric polynomials | certificate: 8.35 \cdot 10^{-4} -> 2.64 \cdot 10^{-4} (d=3, p=5); 2.46 \cdot 10^{-2} -> 3.45 \cdot 10^{-3} (d=4, p=3) | Improved |
| Use GN-big instead of GN-small (ablation) | GloptiNets · Random Chebychev polynomials | certificate: 1.1 \cdot 10^{-2} -> 4.1 \cdot 10^{-3} (p=3); 2.5 \cdot 10^{-2} -> 3.6 \cdot 10^{-3} (p=4) | Improved |
| Use GloptiNets rather than TSSOS | Global optimization with certificates · Small random trigonometric and Chebychev polynomials | certificate: 5.3 \cdot 10^{-11} vs. 8.35 \cdot 10^{-4} (trigonometric, d=3, p=5); 3.4 \cdot 10^{-7} vs. 1.1 \cdot 10^{-2} (Chebychev, | Hurt |
| Apply TSSOS to larger polynomial instances | TSSOS · Random trigonometric and Chebychev polynomials | tractability | Hurt |
| Increase the number of parameters in the k-SoS model (ablation) | GloptiNets · Fixed target function | certificate | Improved |
| Optimize the certificate directly instead of a proxy for the L-infinity norm (ablation) | GloptiNets · Certificate optimization | certificate precision | Improved |
Closest papers by meaning
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.85)
- Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions (ICML 2024 · similarity 0.85)
- GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent (NeurIPS 2024 · similarity 0.85)
- Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization (ICML 2023 · similarity 0.85)
- Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-Loop and Hessian-Free Solution Strategy (ICML 2024 · similarity 0.84)
- Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization (NeurIPS 2025 · similarity 0.84)
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.
