mlsanityData to 7 Oct 2026

Simple And Efficient Architecture Search for Convolutional Neural Networks

arXiv 1711.04528 ↗First posted 13 Nov 2017stat.ML cs.AI cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Neural networks have recently had a lot of success for many tasks. However, neural network architectures that perform well are still typically designed manually by experts in a cumbersome trial-and-error process. We propose a new method to automatically search for well-performing CNN architectures based on a simple hill climbing procedure whose operators apply network morphisms, followed by short optimization runs by cosine annealing. Surprisingly, this simple method yields competitive results, despite only requiring resources in the same order of magnitude as training a single network. E.g., on CIFAR-10, our method designs and trains networks with an error rate below 6% in only 12 hours on a single GPU; training for one day reduces this error further, to almost 5%.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 11; 2023: 6; 2024: 5; 2025: 4; 2026: 1.

40 papers.

Sort:

By area:

  1. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  2. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 76
  3. 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-benchcited by 65
  4. 2022GradMax: Growing Neural Networks using Gradient Informationcited by 64
  5. 2021Firefly Neural Architecture Descent: a General Approach for Growing Neural Networkscited by 48
  6. 2023Visual Tuningcited by 34
  7. 2021The Elastic Lottery Ticket Hypothesiscited by 23
  8. 2021Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimizationcited by 19
  9. 2023Computation-efficient Deep Learning for Computer Vision: A Surveycited by 14
  10. 2021BM-NAS: Bilevel Multimodal Neural Architecture Searchcited by 13
  11. 2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
  12. 2022Neural Architecture Search for Dense Prediction Tasks in Computer Visioncited by 11
28 more
  1. 2021iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretizationcited by 10
  2. 2022AutoLossGen: Automatic Loss Function Generation for Recommender Systemscited by 10
  3. 2026AIRA_2: Overcoming Bottlenecks in AI Research Agentscited by 10
  4. 2022Equivariance-aware Architectural Optimization of Neural Networkscited by 8
  5. 2023Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptationcited by 8
  6. 2025IMPROVE: Iterative Model Pipeline Refinement and Optimization Leveraging LLM Expertscited by 7
  7. 2025SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Sciencecited by 7
  8. 2021Contrastive Self-supervised Neural Architecture Searchcited by 5
  9. 2021Manas: Mining Software Repositories to Assist AutoMLcited by 5
  10. 2021Input Invex Neural Networkcited by 4
  11. 2021Multi-headed Neural Ensemble Searchcited by 4
  12. 2021CONetV2: Efficient Auto-Channel Size Optimization for CNNscited by 4
  13. 2022Distilling the Undistillable: Learning from a Nasty Teachercited by 4
  14. 2023Multi-scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networkscited by 3
  15. 2021A Novel Framework for Neural Architecture Search in the Hill Climbing Domaincited by 2
  16. 2022Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristicscited by 2
  17. 2022Meta-Learning of NAS for Few-shot Learning in Medical Image Applicationscited by 1
  18. 2023Brain-inspired Evolutionary Architectures for Spiking Neural Networkscited by 1
  19. 2024Learning Morphisms with Gauss-Newton Approximation for Growing Networkscited by 1
  20. 2021Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learningcited by 0
  21. 2021Making Differentiable Architecture Search less localcited by 0
  22. 2022A Collaboration Strategy in the Mining Pool for Proof-of-Neural-Architecture Consensuscited by 0
  23. 2022ERNAS: An Evolutionary Neural Architecture Search for Magnetic Resonance Image Reconstructionscited by 0
  24. 2022An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networkscited by 0
  25. 2024Designing deep neural networks for driver intention recognitioncited by 0
  26. 2024Guided Evolution with Binary Discriminators for ML Program Searchcited by 0
  27. 2024Efficient Deep Learning Board: Training Feedback Is Not All You Needcited by 0
  28. 2025Efficient Global Neural Architecture Searchcited by 0