Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep Learning

Abstract

We present Deep-n-Cheap -- an open-source AutoML framework to search for deep learning models. This search includes both architecture and training hyperparameters, and supports convolutional neural networks and multi-layer perceptrons. Our framework is targeted for deployment on both benchmark and custom datasets, and as a result, offers a greater degree of search space customizability as compared to a more limited search over only pre-existing models from literature. We also introduce the technique of 'search transfer', which demonstrates the generalization capabilities of the models found by our framework to multiple datasets. Deep-n-Cheap includes a user-customizable complexity penalty which trades off performance with training time or number of parameters. Specifically, our framework results in models offering performance comparable to state-of-the-art while taking 1-2 orders of magnitude less time to train than models from other AutoML and model search frameworks. Additionally, this work investigates and develops various insights regarding the search process. In particular, we show the superiority of a greedy strategy and justify our choice of Bayesian optimization as the primary search methodology over random / grid search.

Accepted as a conference paper at ACML 2020

References in corpus (10)

• Practical Bayesian Optimization of Machine Learning Algorithms
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• DARTS: Differentiable Architecture Search
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Designing Neural Network Architectures using Reinforcement Learning
• Learning a Driving Simulator
• Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces
• A Kernel for Hierarchical Parameter Spaces