Research map / Optimization / Optimizers
Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity
William de Vazelhes, Hualin Zhang, Huimin Wu, Xiaotong Yuan, Bin Gu
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 smaller number of random directions q (ablation) | SZOHT · toy sparse quadric (d=5000) | f(x) descent | Hurt |
| use q = 1 or 20 random directions (ablation) | SZOHT · toy sparse quadric (d=5000) | distance to optimum | Hurt |
| SZOHT vs ZSCG, RSPGF | SZOHT · sparse asset risk management (port3, port4, port5) | f(x) vs queries | Improved |
| SZOHT vs ZSCG, RSPGF, ZORO | SZOHT · few-pixel adversarial attack (MNIST, CIFAR, ImageNet) | f(x) vs queries | Improved |
| proximal RSPGF vs Frank-Wolfe ZSCG | RSPGF · sparse portfolio and attack tasks | convergence speed | Improved |
| ZORO assumes sparse gradients | ZORO · real-world sparse tasks | early-stage convergence | Hurt |
Closest papers by meaning
- Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise (NeurIPS 2026 · similarity 0.88)
- Refining Adaptive Zeroth-Order Optimization at Ease (ICML 2025 · similarity 0.88)
- Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications (NeurIPS 2024 · similarity 0.87)
- Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations (NeurIPS 2024 · similarity 0.86)
- Zeroth-Order Sharpness-Aware Learning with Exponential Tilting (NeurIPS 2026 · similarity 0.86)
- Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization (ICML 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.
