Research map / Optimization / Optimizers
Guided evolutionary strategies: augmenting random search with surrogate gradients
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 Guided ES, which combines surrogate-gradient guidance with evolutionary-strategy search | Quadratic function with a biased gradient · Random quadratic optimization | loss suboptimality | Helped |
| Use Guided ES instead of vanilla ES | Quadratic function with a biased gradient · Random quadratic optimization | loss suboptimality | Helped |
| Use Guided ES instead of CMA-ES | Quadratic function with a biased gradient · Random quadratic optimization | loss suboptimality | Helped |
| Use Guided ES instead of vanilla ES | Unrolled optimization · Learning-rate prediction with truncated backpropagation | distance from optimal learning rate | Helped |
| Use Guided ES instead of SGD | Unrolled optimization · Learning-rate prediction with truncated backpropagation | distance from optimal learning rate | Helped |
| Use Guided ES with online synthetic-gradient guidance | Synthetic-gradient optimization · Target quadratic optimization | loss | Helped |
| Use Guided ES instead of vanilla ES | Synthetic-gradient optimization · Target quadratic optimization | loss | Helped |
Closest papers by meaning
- Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks (NeurIPS 2026 · similarity 0.88)
- EVOS: Efficient Implicit Neural Training via EVOlutionary Selector (CVPR 2025 · similarity 0.87)
- Gradient Guidance for Diffusion Models: An Optimization Perspective (NeurIPS 2024 · similarity 0.87)
- Diffusion Models are Evolutionary Algorithms (ICLR 2025 · similarity 0.87)
- Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules (NeurIPS 2025 · similarity 0.87)
- ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning (AAAI 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.