Efficient Model Compression for Bayesian Neural Networks
Model Compression has drawn much attention within the deep learning community recently. Compressing a dense neural network offers many advantages including lower computation cost, deployability to devices of limited storage and memories, and resistance to adversarial attacks. This may be achieved via weight pruning or fully discarding certain input features. Here we demonstrate a novel strategy to emulate principles of Bayesian model selection in a deep learning setup. Given a fully connected Bayesian neural network with spike-and-slab priors trained via a variational algorithm, we obtain the posterior inclusion probability for every node that typically gets lost. We employ these probabilities for pruning and feature selection on a host of simulated and real-world benchmark data and find evidence of better generalizability of the pruned model in all our experiments.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Learningfeature selectionmodelModel CompressionModel SelectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Data Compression with Bayesian Attention Networks
The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles.
Data CompressionOn Compression Principle and Bayesian Optimization for Neural Networks
Finding methods for making generalizable predictions is a fundamental problem of machine learning. By looking into similarities between the prediction problem for unknown data and the lossless compression we have found a…
Bayesian OptimizationDimensionality ReductionEnhanced Bayesian Compression via Deep Reinforcement Learning
In this paper, we propose an Enhanced Bayesian Compression method to flexibly compress the deep networks via reinforcement learning. Unlike the existing Bayesian compression method which cannot explicitly enforce quantiz…
Deep Reinforcement LearningQuantizationreinforcement-learningReinforcement Learning+1A Bayesian Optimization Framework for Neural Network Compression
Neural network compression is an important step for deploying neural networks where speed is of high importance, or on devices with limited memory. It is necessary to tune compression parameters in order to achieve the d…
Bayesian OptimizationKnowledge DistillationNeural Network CompressionVariable-Bitrate Neural Compression via Bayesian Arithmetic Coding
Deep Bayesian latent variable models have enabled new approaches to both model and data compression. Here, we propose a new algorithm for compressing latent representations in deep probabilistic models, such as variation…
Data CompressionImage CompressionWord Embeddings