Training generalizable quantized deep neural nets

作者：

Highlights：

• A novel generalizability theory for quantized deep neural nets trained globally.

• The first generalization error bound for tractable local solutions of quantized DL.

• Proposing a provably effective and efficient algorithm for quantized DL models.

摘要

•A novel generalizability theory for quantized deep neural nets trained globally.•The first generalization error bound for tractable local solutions of quantized DL.•Proposing a provably effective and efficient algorithm for quantized DL models.

论文关键词：62M45,68Q32,Deep learning,Quantized neural networks,Generalizability

论文评审过程：Received 23 January 2021, Revised 9 July 2022, Accepted 29 August 2022, Available online 5 October 2022, Version of Record 21 October 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118736