# Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks

Source: [Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks](<https://www.sota2.com/research/paper/68fa65c81e209131cea0c859>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:35:37.665Z

Authors: Mouloud Belbahri, Eyy\\"ub Sari, Sajad Darabi, Vahid Partovi Nia

Published: 2019-01-18T20:39:12.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1901.06414>)

[PDF](<https://arxiv.org/pdf/1901.06414.pdf>)