@article{psandqsquantizationawarepruningfor,
  title = {Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference},
  author = {Benjamin Hawks and Javier Duarte and Nicholas J. Fraser and Alessandro Pappalardo and Nhan Tran and Yaman Umuroglu},
  year = {2021},
  eprint = {2102.11289},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2102.11289v2},
}