| Don’t generate me: Training differentially private generative models with sinkhorn divergence T Cao, A Bie, A Vahdat, S Fidler, K Kreis Advances in Neural Information Processing Systems 34, 12480-12492, 2021 | 51 | 2021 |
| Fully quantizing Transformer-based ASR for edge deployment A Bie, B Venkitesh, J Monteiro, MA Haidar, M Rezagholizadeh ICLR 2021 Workshop on Hardware Aware Efficient Training, 2021 | 33* | 2021 |
| Private estimation with public data A Bie, G Kamath, V Singhal Advances in Neural Information Processing Systems 35, 18653-18666, 2022 | 27 | 2022 |
| Private GANs, Revisited A Bie, G Kamath, G Zhang arXiv preprint arXiv:2302.02936, 2023 | 10 | 2023 |
| Private distribution learning with public data: The view from sample compression S Ben-David, A Bie, CL Canonne, G Kamath, V Singhal Advances in Neural Information Processing Systems 36, 2024 | 9 | 2024 |
| Distribution learnability and robustness S Ben-David, A Bie, G Kamath, T Lechner Advances in Neural Information Processing Systems 36, 2024 | 2 | 2024 |
| Parametric Feature Transfer: One-shot Federated Learning with Foundation Models M Beitollahi, A Bie, S Hemati, LM Brunswic, X Li, X Chen, G Zhang arXiv preprint arXiv:2402.01862, 2024 | 1 | 2024 |
| Private Distribution Learning with Public Data A Bie University of Waterloo, 2024 | | 2024 |
| Differential privacy dataset generation using generative models T Cao, A Bie, KJ Kreis, S Fidler, A Vahdat US Patent 11,847,538, 2023 | | 2023 |
| Understanding the Role of Layer Normalization in Label-Skewed Federated Learning G Zhang, M Beitollahi, A Bie, X Chen Transactions on Machine Learning Research, 0 | | |
