Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU

Schultheis and Babbar. "Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023. doi:10.1007/978-3-031-43418-1_41

[Schultheis and Babbar. "Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023.](https://mlanthology.org/ecmlpkdd/2023/schultheis2023ecmlpkdd-memoryefficient/) doi:10.1007/978-3-031-43418-1_41

@inproceedings{schultheis2023ecmlpkdd-memoryefficient,
  title     = {{Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 670k Labels on a Single Commodity GPU}},
  author    = {Schultheis, Erik and Babbar, Rohit},
  booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
  year      = {2023},
  pages     = {689-704},
  doi       = {10.1007/978-3-031-43418-1_41},
  url       = {https://mlanthology.org/ecmlpkdd/2023/schultheis2023ecmlpkdd-memoryefficient/}
}