# Stochastic Layer-Wise Precision in Deep Neural Networks

arXiv: https://arxiv.org/abs/1807.00942 · HTML: https://mlsanity.com/paper/1807.00942/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

## Built on by (most cited first, 6 of 6)

- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Mixed-Precision Neural Networks: A Survey](https://mlsanity.com/paper/2208.06064/) (2022)
- [Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision](https://mlsanity.com/paper/2411.05845/) (2024)
- [Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey](https://mlsanity.com/paper/2208.10498/) (2022)
- [Constraint Guided Model Quantization of Neural Networks](https://mlsanity.com/paper/2409.20138/) (2024)
- [An Estimator for the Sensitivity to Perturbations of Deep Neural Networks](https://mlsanity.com/paper/2307.12679/) (2023)

## Abstract (arXiv)

Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to adversarial attacks. However, typical implementations of low precision DNNs use uniform precision across all layers of the network. In this work, we explore whether a heterogeneous allocation of precision across a network leads to improved performance, and introduce a learning scheme where a DNN stochastically explores multiple precision configurations through learning. This permits a network to learn an optimal precision configuration. We show on convolutional neural networks trained on MNIST and ILSVRC12 that even though these nets learn a uniform or near-uniform allocation strategy respectively, stochastic precision leads to a favourable regularization effect improving generalization.