Learning Sparse Neural Networks via Sensitivity-Driven Regularization

10/28/2018
by   Enzo Tartaglione, et al.
0

The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (i.e. their relevance to the network output) and introduce a regularization term that gradually lowers the absolute value of parameters with low sensitivity. Thus, a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Our method surpasses most of the recent techniques both in terms of sparsity and error rates. In some cases, the method reaches twice the sparsity obtained by other techniques at equal error rates.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2021

SeReNe: Sensitivity based Regularization of Neurons for Structured Sparsity in Neural Networks

Deep neural networks include millions of learnable parameters, making th...
research
11/16/2020

LOss-Based SensiTivity rEgulaRization: towards deep sparse neural networks

LOBSTER (LOss-Based SensiTivity rEgulaRization) is a method for training...
research
01/07/2019

GASL: Guided Attention for Sparsity Learning in Deep Neural Networks

The main goal of network pruning is imposing sparsity on the neural netw...
research
10/28/2021

Deep Calibration of Interest Rates Model

For any financial institution it is a necessity to be able to apprehend ...
research
08/14/2023

HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization

Sparse neural networks are a key factor in developing resource-efficient...
research
08/23/2023

A multiobjective continuation method to compute the regularization path of deep neural networks

Sparsity is a highly desired feature in deep neural networks (DNNs) sinc...
research
04/12/2022

NARX Identification using Derivative-Based Regularized Neural Networks

This work presents a novel regularization method for the identification ...

Please sign up or login with your details

Forgot password? Click here to reset