Research map / Architectures and efficiency / Neural architecture search
Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution
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 |
|---|---|---|---|
| Search architectures with LEMONADE rather than random search | CIFAR-10 architecture search · CIFAR-10 test, similar model sizes | error (%): 10.0 -> 8.9; 6.3 -> 5.5 | Helped |
| Use LEMONADE architecture search instead of hand-designed or other NAS architectures | CIFAR-10 architecture search · CIFAR-10 test, across model sizes | error (%) | Mixed |
| Use LEMONADE cells rather than baseline cells | ImageNet64x64 transferred architectures · ImageNet64x64 | top-1 validation error | Helped |
| Transfer CIFAR-10-discovered Cell 2 to ImageNet | ImageNet mobile setting · ImageNet | top-1 error (%): 26% -> 28.3% | Hurt |
| Add approximate network morphism operators to allow architectures to shrink (ablation) | LEMONADE · CIFAR-10 | performance | Helped |
| Use Lamarckian inheritance via (approximate) network morphisms instead of initializing networks from scratch (ablation) | LEMONADE · CIFAR-10 | performance | Helped |
| Use KDE-based two-staged sampling instead of uniform sampling of parents and children (ablation) | LEMONADE · CIFAR-10 | performance | Helped |
Closest papers by meaning
- Hierarchical Representations for Efficient Architecture Search (ICLR 2018 · similarity 0.92)
- Meta Architecture Search (NeurIPS 2019 · similarity 0.88)
- Neural Architecture Generator Optimization (NeurIPS 2020 · similarity 0.88)
- Multi-objective Differentiable Neural Architecture Search (ICLR 2025 · similarity 0.87)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · similarity 0.87)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 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.