EigenNas (Zhu et al., 2022)

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology6 results

Neural Architecture SearchonNATS-Bench Topology, ImageNet16-120
Test Accuracy· 2022-09-15
45.54
SOTA
Generalization Properties of NAS under Activation and Skip Connection Search arXiv:2209.07238
AutoMLonNATS-Bench Topology, ImageNet16-120
Test Accuracy· 2022-09-15
45.54
SOTA
Generalization Properties of NAS under Activation and Skip Connection Search arXiv:2209.07238
Neural Architecture SearchonNATS-Bench Topology, CIFAR-10
Test Accuracy· 2022-09-15
93.46
best: 94.13 (RE (Real et al., 2019))
Generalization Properties of NAS under Activation and Skip Connection Search arXiv:2209.07238
Neural Architecture SearchonNATS-Bench Topology, CIFAR-100
Test Accuracy· 2022-09-15
71.42
best: 71.68 (PPO (Schulman et al., 2017))
Generalization Properties of NAS under Activation and Skip Connection Search arXiv:2209.07238
AutoMLonNATS-Bench Topology, CIFAR-10
Test Accuracy· 2022-09-15
93.46
best: 94.13 (RE (Real et al., 2019))
Generalization Properties of NAS under Activation and Skip Connection Search arXiv:2209.07238
AutoMLonNATS-Bench Topology, CIFAR-100
Test Accuracy· 2022-09-15
71.42
best: 71.68 (PPO (Schulman et al., 2017))
Generalization Properties of NAS under Activation and Skip Connection Search arXiv:2209.07238