@article{acceleratingdeeplearninginferencevia1,
  title = {Accelerating Deep Learning Inference via Learned Caches},
  author = {Arjun Balasubramanian and Adarsh Kumar and YuHan Liu and Han Cao and Shivaram Venkataraman and Aditya Akella},
  year = {2021},
  eprint = {2101.07344},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2101.07344v1},
}