paper-with-me

홈 › Papers

MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search

2020-09-19 · Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki

In neural architecture search (NAS), differentiable architecture search (DARTS) has recently attracted much attention due to its high efficiency. It defines an over-parameterized network with mixed edges, each of which represents all operator candidates, and jointly optimizes the weights of the network and its architecture in an alternating manner. However, this method finds a model with the weights converging faster than the others, and such a model with fastest convergence often leads to overfitting. Accordingly, the resulting model cannot always be well-generalized. To overcome this problem, we propose a method called minimum stable rank DARTS (MSR-DARTS), for finding a model with the best generalization error by replacing architecture optimization with the selection process using the minimum stable rank criterion. Specifically, a convolution operator is represented by a matrix, and MSR-DARTS selects the one with the smallest stable rank. We evaluated MSR-DARTS on CIFAR-10 and ImageNet datasets. It achieves an error rate of 2.54% with 4.0M parameters within 0.3 GPU-days on CIFAR-10, and a top-1 error rate of 23.9% on ImageNet. The official code is available at https://github.com/mtaecchhi/msrdarts.git.

📄 PDF Abstract BibTeX arXiv:2009.09209

Code (0)

등록된 구현이 없습니다.

Tasks

GPUNeural Architecture Search

Methods 이 논문이 사용한 방법론

DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Single-DARTS: Towards Stable Architecture Search

2021-08-18 · Pengfei Hou, Ying Jin, Yukang Chen

Differentiable architecture search (DARTS) marks a milestone in Neural Architecture Search (NAS), boasting simplicity and small search costs. However, DARTS still suffers from frequent performance collapse, which happens…

Neural Architecture Search

iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization

2021-08-25 · Huiqun Wang, Ruijie Yang, Di Huang, Yunhong Wang

Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation of network representation and dramatically accelerates Neural Architecture Search (NAS) by almost thousands of times in GPU-day. However, the search…

GPUNeural Architecture Search

Neighborhood-Aware Neural Architecture Search

2021-05-13 · Xiaofang Wang, Shengcao Cao, Mengtian Li, Kris M. Kitani

Existing neural architecture search (NAS) methods often return an architecture with good search performance but generalizes poorly to the test setting. To achieve better generalization, we propose a novel neighborhood-aw…

Neural Architecture Search

DARTS-PRIME: Regularization and Scheduling Improve Constrained Optimization in Differentiable NAS

2021-06-22 · Kaitlin Maile, Erwan Lecarpentier, Hervé Luga, Dennis G. Wilson

Differentiable Architecture Search (DARTS) is a recent neural architecture search (NAS) method based on a differentiable relaxation. Due to its success, numerous variants analyzing and improving parts of the DARTS framew…

Bilevel OptimizationNeural Architecture SearchScheduling

DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search

2021-11-23 · BMVC 2021 11 · Shun Lu, Yu Hu, Longxing Yang, Zihao Sun 외

Differentiable Neural Architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency. However, the competition of candidate operations in DARTS introduces high uncertainty for se…

Neural Architecture Search