Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?

By Yunyang Xiong, Ronak R. Mehta, Vikas Singh. 2019

38 citations recorded by the source corpus.

The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning strategies performed over distinct discrete architecture choices. In the latter case, the optimization is often non-differentiable and also not very amenable to derivative-free optimization methods. Most methods in use today require sizable computational resources. And if we want networks that additionally satisfy resource constraints, the above challenges are exacerbated because the search must now balance accuracy with certain budget constraints on resources. We formulate this problem as the optimization of a set function -- we find that the empirical behavior of this set function often (but not always) satisfies marginal gain and monotonicity principles -- properties central to the idea of submodularity. Based on this observation, we adapt algorithms within discrete optimization to obtain heuristic schemes for neural network architecture search, where we have resource constraints on the architecture. This simple scheme when applied on CIFAR-100 and ImageNet, identifies resource-constrained architectures with quantifiably better performance than current state-of-the-art models designed for mobile devices. Specifically, we find high-performing architectures with fewer parameters and computations by a search method that is much faster.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Po-Yao (Bernie) Huang
2. Xiaojun Chang
3. Zhihui Li
4. Xin Wang
5. Xiaojiang Chen
6. Yun Xiao
7. Pengzhen Ren

In Computer Vision and Pattern Recognition

1. Po-Yao (Bernie) Huang
2. Zhihui Li
3. Xiaojun Chang
4. Xin Wang
5. Xiaojiang Chen
6. Yun Xiao
7. Pengzhen Ren

Citations in the corpus

• A Comprehensive Survey of Neural Architecture Search (2020, background): “…also quickly applied in the fields of object detection [65, 75, 111, 118], semantic segmentation [63, 64, 120], adversarial learning [53], architectural scaling [114, 122, 124], multi-objective optimization [39, 115, 125], platform-aware [28, 34, 103, 117], data augmentation [121, 123] and so on.”
• CARS: Continuous Evolution for Efficient Neural Architecture Search (2019, unknown): “5 375 20 gradient RCNet [47] 72.”