Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks
This addresses the challenge of poor generalization in compressed neural networks for edge computing applications, though it appears incremental as it builds on existing quantization and regularization techniques.
The paper tackles the problem of deploying deep neural networks on edge devices by introducing the foothill function, a quasiconvex regularizer that reduces the accuracy gap between binary neural networks and full-precision models on ImageNet.
Deep neural networks (DNNs) have demonstrated success for many supervised learning tasks, ranging from voice recognition, object detection, to image classification. However, their increasing complexity might yield poor generalization error that make them hard to be deployed on edge devices. Quantization is an effective approach to compress DNNs in order to meet these constraints. Using a quasiconvex base function in order to construct a binary quantizer helps training binary neural networks (BNNs) and adding noise to the input data or using a concrete regularization function helps to improve generalization error. Here we introduce foothill function, an infinitely differentiable quasiconvex function. This regularizer is flexible enough to deform towards $L_1$ and $L_2$ penalties. Foothill can be used as a binary quantizer, as a regularizer, or as a loss. In particular, we show this regularizer reduces the accuracy gap between BNNs and their full-precision counterpart for image classification on ImageNet.