Improved Bayesian Compression

Abstract

Compression of Neural Networks (NN) has become a highly studied topic in recent years. The main reason for this is the demand for industrial scale usage of NNs such as deploying them on mobile devices, storing them efficiently, transmitting them via band-limited channels and most importantly doing inference at scale. In this work, we propose to join the Soft-Weight Sharing and Variational Dropout approaches that show strong results to define a new state-of-the-art in terms of model compression.

References in corpus (3)

• Learning Structured Sparsity in Deep Neural Networks
• Bayesian Compression for Deep Learning
• Soft Weight-Sharing for Neural Network Compression

Cited by in corpus (5)

• DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
• Rate Distortion For Model Compression: From Theory To Practice
• Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)
• Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
• Structured Bayesian Compression for Deep models in mobile enabled devices for connected healthcare