Information-Theoretic Understanding of Population Risk Improvement with Model Compression

Abstract

We show that model compression can improve the population risk of a pre-trained model, by studying the tradeoff between the decrease in the generalization error and the increase in the empirical risk with model compression. We first prove that model compression reduces an information-theoretic bound on the generalization error; this allows for an interpretation of model compression as a regularization technique to avoid overfitting. We then characterize the increase in empirical risk with model compression using rate distortion theory. These results imply that the population risk could be improved by model compression if the decrease in generalization error exceeds the increase in empirical risk. We show through a linear regression example that such a decrease in population risk due to model compression is indeed possible. Our theoretical results further suggest that the Hessian-weighted $K$-means clustering compression approach can be improved by regularizing the distance between the clustering centers. We provide experiments with neural networks to support our theoretical assertions.

arXiv commentsubmitted to ICML 2019

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Compressing Deep Convolutional Networks using Vector Quantization
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Quantizing deep convolutional networks for efficient inference: A whitepaper
• Trained Ternary Quantization
• Convolutional neural networks with low-rank regularization
• A Survey on Methods and Theories of Quantized Neural Networks
• Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
• Towards the Limit of Network Quantization
• Rate Distortion For Model Compression: From Theory To Practice