.png){kind=icon}
.png){kind=icon}
Return
Bayesian Automatic Model Compression
.png){kind=icon}
PRE
AI
DOI：10.1109/JSTSP.2020.2977090.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Model compression has drawn great attention in deep learning community. A core problem in model compression is to determine the layer-wise optimal compression policy, e.g., the layer-wise bit-width in network quantization. Conventional hand-crafted heuristics rely on human experts and are usually sub-optimal, while recent reinforcement learning based approaches can be inefficient during the exploration of the policy space. In this article, we propose Bayesian automatic model compression (BAMC), which leverages non-parametric Bayesian methods to learn the optimal quantization bit-width for each layer of the network. BAMC is trained in a one-shot manner, avoiding the back and forth (re)-training in reinforcement learning based approaches. Experimental results on various datasets validate that our proposed methods can find reasonable quantization policies efficiently with little accuracy drop for the quantized network.
Keywords:
Quantization (signal)
Bayes methods
Mathematical model
Training
Mixture models
Optimization
Machine learning
Bayesian learning
model compression
automatic machine learning
quantizartion
explainability
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.9K
Citations:
1.1W