DARTS-: Robustly Stepping out of Performance Collapse Without Indicators

Authors: Xiangxiang Chu, Xiaoxing Wang, Bo Zhang, Shun Lu, Xiaolin Wei, Junchi Yan

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on various datasets verify that it can substantially improve robustness.
Researcher Affiliation Collaboration 1Meituan, 2Shanghai Jiao Tong University, 3University of Chinese Academy of Sciences
Pseudocode Yes Algorithm 1 DARTS
Open Source Code Yes Our code is available at https://github.com/Meituan-Auto ML/DARTS-.
Open Datasets Yes Extensive experiments on various datasets verify that it can substantially improve robustness. Our code is available at https://github.com/Meituan-Auto ML/DARTS-. ... We conduct thorough experiments across seven search spaces and three datasets to demonstrate the effectiveness of our method. ... CIFAR-10 and CIFAR-100. ... Image Net. ... NAS-Bench-201 (Dong & Yang, 2020)
Dataset Splits Yes min α Lval(w (α), α) s.t. w (α) = arg min w Ltrain(w, α)
Hardware Specification Yes It takes about 4.5 GPU days on Tesla V100.
Software Dependencies No The paper mentions using SGD and Adam optimizers and general settings for training (e.g., learning rate, batch size) but does not specify software versions for libraries like PyTorch, TensorFlow, or CUDA.
Experiment Setup Yes We use the SGD optimizer for weight and Adam (β1 = 0.5 and β2 = 0.999, 0.001 learning rate) for architecture parameters with the batch-size of 768. The initial learning rate is 0.045 and decayed to 0 within 30 epochs following the cosine schedule. We also use L2 regularization with 1e-4.