Research map / Optimization / Nonconvex and smooth optimization
Noisy Pairwise-Comparison Random Search for Smooth Nonconvex Optimization
Taha EL BAKKALI EL KADI, Rayane Bouftini, Qiuyi Zhang, Omar Saadi
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 |
|---|---|---|---|
| lower intrinsic dimension of the fine-tuning task | NCRS, MeZO, RSGF · GLUE MRPC/QQP LM fine-tuning | iterations to reach SGD accuracy | Improved |
| use NCRS instead of RSGF | NCRS · GLUE MRPC/QQP LM fine-tuning | iterations to reach SGD accuracy | Improved |
| use MeZO instead of NCRS | MeZO · GLUE MRPC/QQP LM fine-tuning | iterations to reach SGD accuracy | Mixed |
| increase model size with sufficient pretraining | zeroth-order methods · GLUE MRPC/QQP LM fine-tuning | iterations | Improved |
| use NCRS with confidence-weighted vote for preference RL | NCRS · DM Control Suite preference RL | ground truth reward | No clear effect |
Closest papers by meaning
- Stochastic Optimization with Random Search (NeurIPS 2026 · similarity 0.89)
- Oracle Complexity in Nonsmooth Nonconvex Optimization (NeurIPS 2021 · similarity 0.89)
- A Tale of Two Smoothness Notions: Adaptive Optimizers and Non-Euclidean Descent (ICLR 2026 · similarity 0.87)
- Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits (NeurIPS 2020 · similarity 0.87)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.86)
- Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization (NeurIPS 2024 · similarity 0.86)
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.
