paper-with-me

홈 › Papers

Efficient Model Compression for Bayesian Neural Networks

2024-11-01 · Diptarka Saha, Zihe Liu, Feng Liang

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.

📄 PDF Abstract BibTeX arXiv:2411.00273

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Learningfeature selectionmodelModel CompressionModel Selection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Pruning 설명 없음
Feature Selection Feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables,…

Similar Papers 제목 키워드 기반

Data Compression with Bayesian Attention Networks

2021-03-04 · Anonymous

The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles.

Data Compression

On Compression Principle and Bayesian Optimization for Neural Networks

2020-06-23 · Michael Tetelman

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 Reduction

Enhanced Bayesian Compression via Deep Reinforcement Learning

2019-06-01 · CVPR 2019 6 · Xin Yuan, Liangliang Ren, Jiwen Lu, Jie Zhou

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+1

A Bayesian Optimization Framework for Neural Network Compression

2019-10-01 · ICCV 2019 10 · Xingchen Ma, Amal Rannen Triki, Maxim Berman, Christos Sagonas 외

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 Compression

Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding

2020-01-01 · ICML 2020 1 · Yibo Yang, Robert Bamler, Stephan Mandt

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