Publications

• Under review
  • Bu, Z., Zhang, X., Hong, M., Zha, S. and Karypis, G., 2024. Pre-training Differentially Private Models with Limited Public Data. arXiv preprint arXiv:2402.18752. Submitted to NeurIPS 2024.
  • Zhang, X., Bu, Z., Hong, M. and Razaviyayn, M., 2024. DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction. arXiv preprint arXiv:2408.13460. Submitted to NeurIPS 2024.
  • Li, Z., Zhang, X. and Razaviyayn, M., Addax: Memory-Efficient Fine-Tuning of Language Models with a Combination of Forward-Backward and Forward-Only Passes. In 5th Workshop on practical ML for limited/low resource settings. Submitted to NeurIPS 2024.
• 2024
  • Zhang, X., Hong. M, & Chen, J. GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data, Transactions on Machine Learning Research, 2024.
  • Tian, Y., Zuniga, A., Zhang, X., Dürholt, J.P., Das, P., Chen, J., Matusik, W. and Lukovic, M.K., Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints. In Forty-first International Conference on Machine Learning.
  • Zhang, X., Bu, Z., Wu, S. and Hong, M., Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach. In The Twelfth International Conference on Learning Representations.
  • Zhang, X., Song, B., Honarkhah, M., Dingl, J. and Hong, M., 2024, July. Building Large Models from Small Distributed Models: A Layer Matching Approach. In 2024 IEEE 13rd Sensor Array and Multichannel Signal Processing Workshop (SAM) (pp. 1-5). IEEE.
• 2023
  • Zhang, X., Hong, M. and Elia, N., 2023. Understanding a class of decentralized and federated optimization algorithms: A multirate feedback control perspective. SIAM Journal on Optimization, 33(2), pp.652-683.
  • Zhang, X., Hong, M., & Elia, N. A Unified Framework to Understand Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective, SIAM Journal on Optimization, (NeurIPS-2021 Workshop on New Frontiers in Federated Learning. (Accepted as Contributed Talk))
  • Song, B., Khanduri, P., Zhang, X., Yi, J. and Hong, M., 2023, July. Fedavg converges to zero training loss linearly for overparameterized multi-layer neural networks. In International Conference on Machine Learning (pp. 32304-32330). PMLR.
• 2022
  • Zhang, X., Hong, M., Dhople S., & Elia, N. A Stochastic Multi-Rate Control Framework For Modeling Distributed Optimization Algorithms, International Conference on Machine Learning, 2022. (Accept for Spotlight Presentation) https://proceedings.mlr.press/v162/zhang22j.html
  • Zhang, X., Chen, X., Hong, M., Wu, Z.S. & Yi, J. Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy, International Conference on Machine Learning, 2022. (Accept for Spotlight Presentation) https://proceedings.mlr.press/v162/zhang22b.html
  • Liu Y., Zhang X., Kang Y., Li L., & Hong M. FedBCD: A Communication-Efficient Collaborative Learning Framework for Distributed Features, IEEE Transactions on Signal Processing, 2022, IEEE. https://ieeexplore.ieee.org/document/9855231 (Co-first author and corresponding author).
• 2021
  • Zhang, X., Hong, M., Dhople, S., Yin, W., & Liu, Y. FedPD: A Federated Learning Framework with Adaptivity to Non-IID Data. IEEE Transactions on Signal Processing, 2022, IEEE. https://ieeexplore.ieee.org/document/9556559
• 2020
  • Chang, T. H., Hong, M., Wai, H. T., Zhang, X., & Lu, S. Distributed learning in the nonconvex world: From batch data to streaming and beyond. IEEE Signal Processing Magazine, 37(3), 26-38.
  • Zhang, X., Yin, W., Hong, M. & Chen, T. Hybrid FL: Algorithms and Implementation, Conference on Neural Information Processing Systems 2020 Workshop on Scalability, Privacy, and Security in Federated Learning. (Best Student Paper Award)
  • Zhang, X., Purba, V., Hong, M., & Dhople, S. A sum-of-squares optimization method for learning and controlling photovoltaic systems. In 2020 American Control Conference (ACC) (pp. 2376-2381). IEEE.
• 2019
  • Zhang, X., Sartori, J., Hong, M., & Dhople, S. Implementing First-order Optimization Methods: Algorithmic Considerations and Bespoke Microcontrollers. In 2019 53rd Asilomar Conference on Signals, Systems, and Computers (pp. 296-300). IEEE.
  • Lu, S., Zhang, X., Sun, H., & Hong, M. GNSD: A gradient-tracking based nonconvex stochastic algorithm for decentralized optimization. In 2019 IEEE Data Science Workshop (DSW) (pp. 315-321). IEEE.
• 2018
  • Zhang, X., Du, Y., Chen, F., Qin, L., & Ling, Q. Indoor Position Control of a Quadrotor UAV with Monocular Vision Feedback. In 2018 37th Chinese Control Conference (CCC) (pp. 9760-9765). IEEE.
  • Du, Y., Zhang, X., Qin, L., Wu, G., & Ling, Q. State estimation of autonomous rotorcraft MAVs under indoor environments. In 2018 Chinese Control And Decision Conference (CCDC) (pp. 4420-4424). IEEE.

You can also find my articles on my Google Scholar profile