| To supervise or not to supervise: How to effectively learn wireless interference management models? B Song, H Sun, W Pu, S Liu, M Hong 2021 IEEE 22nd International Workshop on Signal Processing Advances in …, 2021 | 8 | 2021 |
| Fedavg converges to zero training loss linearly for overparameterized multi-layer neural networks B Song, P Khanduri, X Zhang, J Yi, M Hong International Conference on Machine Learning, 32304-32330, 2023 | 4* | 2023 |
| Distributed optimization for overparameterized problems: Achieving optimal dimension independent communication complexity B Song, I Tsaknakis, CY Yau, HT Wai, M Hong Advances in Neural Information Processing Systems 35, 6147-6160, 2022 | 4 | 2022 |
| Building large machine learning models from small distributed models: A layer matching approach X Zhang, B Song, M Honarkhah, J Ding, M Hong Workshop on Federated Learning: Recent Advances and New Challenges (in …, 2022 | 1 | 2022 |
| Low-rank matrix completion for distributed ambient noise imaging systems D Xu, B Song, Y Xie, SM Wu, FC Lin, WZ Song 2019 53rd Asilomar Conference on Signals, Systems, and Computers, 1059-1065, 2019 | 1 | 2019 |
| Privacy-preserving federated learning: algorithms and guarantees X Zhang, X Chen, B Song, P Khanduri, M Hong Federated Learning, 57-74, 2024 | | 2024 |
| Transformer Based Approach for Wireless Resource Allocation Problems Involving Mixed Discrete and Continuous Variables B Song, Z Zhou, C Li, D Guo, X Fu, M Hong 2023 IEEE 24th International Workshop on Signal Processing Advances in …, 2023 | | 2023 |
| To Supervise or Not: How to Effectively Learn Wireless Interference Management Models? B Song, H Sun, W Pu, S Liu, M Hong arXiv preprint arXiv:2112.14011, 2021 | | 2021 |
