paper-with-me

홈 › Papers

Pruning a neural network using Bayesian inference

2023-08-04 · Sunil Mathew, Daniel B. Rowe

Neural network pruning is a highly effective technique aimed at reducing the computational and memory demands of large neural networks. In this research paper, we present a novel approach to pruning neural networks utilizing Bayesian inference, which can seamlessly integrate into the training procedure. Our proposed method leverages the posterior probabilities of the neural network prior to and following pruning, enabling the calculation of Bayes factors. The calculated Bayes factors guide the iterative pruning. Through comprehensive evaluations conducted on multiple benchmarks, we demonstrate that our method achieves desired levels of sparsity while maintaining competitive accuracy.

📄 PDF Abstract BibTeX arXiv:2308.02451

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian InferenceNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Principled Pruning of Bayesian Neural Networks through Variational Free Energy Minimization

2022-10-17 · Jim Beckers, Bart van Erp, Ziyue Zhao, Kirill Kondrashov 외

Bayesian model reduction provides an efficient approach for comparing the performance of all nested sub-models of a model, without re-evaluating any of these sub-models. Until now, Bayesian model reduction has been appli…

BMRS: Bayesian Model Reduction for Structured Pruning

2024-06-03 · Dustin Wright, Christian Igel, Raghavendra Selvan

Modern neural networks are often massively overparameterized leading to high compute costs during training and at inference. One effective method to improve both the compute and energy efficiency of neural networks while…

model

On the optimization and pruning for Bayesian deep learning

2022-10-24 · Xiongwen Ke, Yanan Fan

The goal of Bayesian deep learning is to provide uncertainty quantification via the posterior distribution. However, exact inference over the weight space is computationally intractable due to the ultra-high dimensions o…

Deep LearningUncertainty QuantificationVariational Inference

Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study

2020-05-23 · Himanshu Sharma, Elise Jennings

Bayesian neural Networks (BNNs) are a promising method of obtaining statistical uncertainties for neural network predictions but with a higher computational overhead which can limit their practical usage. This work explo…

BenchmarkingNetwork Pruning

Bayesian Bits: Unifying Quantization and Pruning

2020-05-14 · NeurIPS 2020 12 · Mart van Baalen, Christos Louizos, Markus Nagel, Rana Ali Amjad 외

We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization. Bayesian Bits employs a novel decomposition of the quantization operation, which sequ…

Quantization