Research map / Optimization / Nonconvex and smooth optimization
A Simple and Efficient Smoothing Method for Faster Optimization and Local Exploration
Kevin Scaman, Ludovic DOS SANTOS, Merwan Barlier, Igor Colin
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 BMR smoothing instead of randomized smoothing (RS) | zeroth-order smoothing optimizer · f_R (non-symmetric piecewise linear) | normalized progress (f(x0)-f(xt))/(f(x0)-f(x*)) | Improved |
| couple alpha and gamma with exponential gamma decay schedule (alpha proportional to gamma^-2) | BMR · f_PWL piecewise linear | normalized progress | Improved |
| choose too small an initial gamma | RS and BMR · f_PWL piecewise linear | normalized progress | Hurt |
| increase alpha | BMR · f_F Fourier function | normalized progress | Improved |
| increase alpha from 10 to 100 | BMR · f_F and f_FC | normalized progress | Mixed |
| use BMR instead of RS | smoothing optimizer · f_FC (clipped Fourier) | normalized progress | Hurt |
| increase alpha | BMR · f_F and f_FC | gradient norm at convergence | Improved |
Closest papers by meaning
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.89)
- Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization (ICML 2024 · similarity 0.88)
- Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization (NeurIPS 2025 · similarity 0.87)
- Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimization (ICML 2025 · similarity 0.87)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.87)
- Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity (NeurIPS 2025 · similarity 0.87)
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.
