Research map / Optimization / Nonconvex and smooth optimization
Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 cyclic block updates instead of simultaneous full-gradient updates | SCCD vs SGD · CIFAR-10 LeNet | convergence and test accuracy | Helped |
| Use cyclic block updates instead of simultaneous full-gradient updates | VRO-CCD vs PAGE · CIFAR-10 LeNet | convergence and test accuracy | Helped |
| Use VRO-CCD rather than PAGE | LeNet training · CIFAR-10 | runtime per epoch: 20.7 ± 0.9 -> 49.5 ± 2.3 | Hurt |
| Use SCCD rather than SGD | LeNet training · CIFAR-10 | runtime per iteration: 0.172 -> 0.185 | Hurt |
| Remove recursive variance reduction by setting p = 1 (ablation) | VRO-CCD · CIFAR-10 LeNet | runtime per iteration: 0.041 -> 0.185 | Mixed |
Closest papers by meaning
- Stochastic Variance Reduction for Nonconvex Optimization (ICML 2016 · similarity 0.90)
- Variance Reduction for Faster Non-Convex Optimization (ICML 2016 · similarity 0.89)
- Stochastic Nested Variance Reduction for Nonconvex Optimization (NeurIPS 2018 · similarity 0.88)
- Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems (NeurIPS 2020 · similarity 0.88)
- Coordinate Descent Methods for DC Minimization: Optimality Conditions and Global Convergence (AAAI 2023 · similarity 0.88)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · 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.