| Distributed statistical machine learning in adversarial settings: Byzantine gradient descent Y Chen, L Su, J Xu Proceedings of the ACM on Measurement and Analysis of Computing Systems 1 (2 …, 2017 | 710 | 2017 |
| Byzantine Multi-Agent Optimization: Part II L Su, N Vaidya arXiv preprint arXiv:1507.01845, 2015 | 189* | 2015 |
| Securing distributed machine learning in high dimensions L Su, J Xu SIGMETRICS 2019 arXiv preprint arXiv:1804.10140, 2018 | 99* | 2018 |
| Byzantine-resilient multiagent optimization L Su, NH Vaidya IEEE Transactions on Automatic Control 66 (5), 2227-2233, 2020 | 73 | 2020 |
| Finite-time guarantees for Byzantine-resilient distributed state estimation with noisy measurements L Su, S Shahrampour Transactions on Automatic Control (TAC), 2020 | 66 | 2020 |
| Defending Non-Bayesian Learning against Adversarial Attacks L Su, NH Vaidya Distributed Computing arXiv: 1606.08883, 2016 | 56 | 2016 |
| On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective L Su, P Yang NeurIPS2019, 2019 | 52 | 2019 |
| Reaching approximate Byzantine consensus with multi-hop communication L Su, NH Vaidya Information and Computation 255, 352-368, 2017 | 46 | 2017 |
| Non-bayesian learning in the presence of byzantine agents L Su, NH Vaidya Distributed Computing: 30th International Symposium, DISC 2016, Paris …, 2016 | 40 | 2016 |
| Multi-agent optimization in the presence of Byzantine adversaries: Fundamental limits LSN Vaidya 2016 American Control Conference (ACC), 7183-7188, 2016 | 37 | 2016 |
| Fault-tolerant distributed optimization (Part IV): Constrained optimization with arbitrary directed networks L Su, NH Vaidya arXiv preprint arXiv:1511.01821, 2015 | 27 | 2015 |
| Spike-Based Winner-Take-All Computation: Fundamental Limits and Order-Optimal Circuits L Su, CJ Chang, N Lynch Neural Computation 31, 2523-2561, 2019 | 22 | 2019 |
| Asynchronous distributed hypothesis testing in the presence of crash failures L Su, NH Vaidya arXiv preprint arXiv:1606.03418, 2016 | 17 | 2016 |
| Defending distributed systems against adversarial attacks: consensus, consensusbased learning, and statistical learning L Su ACM SIGMETRICS Performance Evaluation Review 47 (3), 24-27, 2020 | 15 | 2020 |
| Robust multi-agent optimization: coping with byzantine agents with input redundancy L Su, NH Vaidya International Symposium on Stabilization, Safety, and Security of …, 2016 | 14 | 2016 |
| Collaboratively learning the best option on graphs, using bounded local memory L Su, M Zubeldia, N Lynch Proceedings of the ACM on Measurement and Analysis of Computing Systems 3 (1 …, 2019 | 11 | 2019 |
| Experimental design networks: A paradigm for serving heterogeneous learners under networking constraints Y Li, Y Liu, L Su, E Yeh, S Ioannidis IEEE/ACM Transactions on Networking 31 (5), 2236-2250, 2023 | 10 | 2023 |
| Distributed learning over time-varying graphs with adversarial agents P Vyavahare, L Su, NH Vaidya 2019 22th International Conference on Information Fusion (FUSION), 1-8, 2019 | 9 | 2019 |
| Distributed Learning with Adversarial Agents Under Relaxed Network Condition P Vyavahare, L Su, NH Vaidya Fusion 2019, 2019 | 9 | 2019 |
| A Non-parametric View of FedAvg and FedProx: Beyond Stationary Points L Su, J Xu, P Yang Accepted to Journal of Machine Learning Research (JMLR), 2021 | 8 | 2021 |
Nitin H. VaidyaGeorgetown University在 georgetown.edu 的电子邮件经过验证
