Publications

Chuanhao Li, Huazheng Wang, Mengdi Wang and Hongning Wang. Communication Efficient Distributed Learning for Kernelized Contextual Bandits. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS’2022), 2022.

Chuanhao Li and Hongning Wang. Communication Efficient Federated Learning for Generalized Linear Bandits. Thirtysixth Conference on Neural Information Processing Systems (NeurIPS’2022), 2022.

Chuanhao Li, Huazheng Wang, Mengdi Wang and Hongning Wang. Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment. The Tenth International Conference on Learning Representations (ICLR’2023).

Xida Ren, Alif Ahmed, Yizhou Wei, Kevin Skadron, Ashish Venkat. ProxyVM: A Scalable and Retargetable Compiler Framework for Privacy-Aware Proxy Workload Generation. In Semiconductor Research Corporation’s Annual Technical Conference (SRC TECHCON 2022).

Uday Kiran and Ashish Venkat. Automatic Generation of Privacy-Preserving Clones of COTS Binaries. In Preparation to the Fifty-First International Symposium on Computer Architecture (ISCA-51).

Samuel Maddock, Graham Cormode, Tianhao Wang, Carsten Maple, and Somesh Jha. “Federated boosted decision trees with differential privacy.” In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pp. 2249-2263. 2022.

Junyi Li, Heng Huang. “Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning”. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), in press.

Junyi Li, Feihu Huang, Heng Huang. “Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems”. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), in press.

Wenhan Xian, Heng Huang. “Finding Local Minima Efficiently in Decentralized Optimization”. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), in press.

Xidong Wu, Jianhui Sun, Zhengmian Hu, Junyi Li, Aidong Zhang, Heng Huang. “Federated Conditional Stochastic Optimization”. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), in press.

Xidong Wu, Jianhui Sun, Zhengmian Hu, Aidong Zhang, Heng Huang. “Solving a Class of NonConvex Minimax Optimization in Federated Learning”. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), in press.

Zhengmian Hu, Heng Huang. “Optimization and Bayes: A Trade-off for Overparameterized Neural Networks”. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), in press.

Zhengmian Hu, Heng Huang. “Tighter Analysis for ProxSkip”. Fortieth International Conference on Machine Learning (ICML 2023), pp. 13469–13496.

Zhengmian Hu, Xidong Wu, Heng Huang. “Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization”. Fortieth International Conference on Machine Learning (ICML 2023), pp. 13652–13678.

Xidong Wu, Zhengmian Hu, Jian Pei, Heng Huang. “Serverless Biased Stochastic Methods for Multi[1]Party Collaborative Imbalanced Data Mining”. 29th SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2023), pp. 2648–2659.

Xidong Wu, Zhengmian Hu, Heng Huang. “Decentralized Riemannian Algorithm for Nonconvex Minimax Problems”. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), pp. 10370–10378.

Xidong Wu, Feihu Huang, Zhengmian Hu, Heng Huang. “Faster Adaptive Federated Learning”. Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), pp. 10379–10387.

Feihu Huang, Junyi Li, Shangqian Gao, Heng Huang. “Enhanced Bilevel Optimization via Bregman Distance”. Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS 2022), pp. 28928–28939.

Xidong Wu, Feihu Huang, Heng Huang. “Fast Stochastic Recursive Momentum Methods for Imbalanced Data Mining”. The 22nd IEEE International Conference on Data Mining (ICDM 2022), pp. 578–587.

Wenhan Xian, Feihu Huang, Heng Huang. “Communication-Efficient Adam-Type Algorithms for Distributed Data Mining”. The 22nd IEEE International Conference on Data Mining (ICDM 2022), pp. 1245–1250.

Jinming Zhuang, Zhuoping Yang, Peipei Zhou. High Performance, Low Power Matrix Multiply Design on ACAP: from Architecture, Design Challenges and DSE Perspectives. 60th ACM/IEEE Design Automation Conference, San Francisco, California, USA, (DAC’23)

Jinming Zhuang, Jason Lau, Hanchen Ye, Zhuoping Yang, Yubo Du, Jack Lo, Kristof Denolf, Stephen Neuendorffer, Alex K. Jones, Jingtong Hu, Deming Chen, Jason Cong, Peipei Zhou. CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture. Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA’23)