Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure

TL;DR

This paper introduces an automated deep auto compression method using reinforcement learning with an actor-critic structure, achieving significant FLOP reduction and improved accuracy without human intervention.

Contribution

It presents a novel reinforcement learning framework for neural network compression that automates feature exploration and model optimization.

Findings

4-fold reduction in FLOP

2.8% higher accuracy than manual methods on VGG-16

Automated compression without human effort

Abstract

Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore specialized areas for exploration and design of large spaces in terms of size, speed, and accuracy, which usually have returns Less and time is up. This paper will effectively analyze deep auto compression (ADC) and reinforcement learning strength in an effective sample and space design, and improve the compression quality of the model. The results of compression of the advanced model are obtained without any human effort and in a completely automated way. With a 4- fold reduction in FLOP, the accuracy of 2.8% is higher than the manual compression model for VGG-16 in ImageNet.