no code implementations • 24 Mar 2024 • Mohammadreza Pourreza, Davood Rafiei, Yuxi Feng, Raymond Li, Zhenan Fan, Weiwei Zhang
Furthermore, compared to these competitive models, our proposed encoder enhances the downstream performance of NL2SQL models in 1-shot in-context learning scenarios by 1-2\% for GPT-3. 5-turbo, 4-8\% for CodeLlama-7B, and 2-3\% for CodeLlama-13B.
no code implementations • 11 Jan 2024 • Xijun Li, Fangzhou Zhu, Hui-Ling Zhen, Weilin Luo, Meng Lu, Yimin Huang, Zhenan Fan, Zirui Zhou, Yufei Kuang, Zhihai Wang, Zijie Geng, Yang Li, Haoyang Liu, Zhiwu An, Muming Yang, Jianshu Li, Jie Wang, Junchi Yan, Defeng Sun, Tao Zhong, Yong Zhang, Jia Zeng, Mingxuan Yuan, Jianye Hao, Jun Yao, Kun Mao
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
no code implementations • 6 Jan 2024 • Zhenan Fan, Bissan Ghaddar, Xinglu Wang, Linzi Xing, Yong Zhang, Zirui Zhou
The rapid advancement of artificial intelligence (AI) techniques has opened up new opportunities to revolutionize various fields, including operations research (OR).
1 code implementation • 16 Aug 2022 • Zhenan Fan, Zirui Zhou, Jian Pei, Michael P. Friedlander, Jiajie Hu, Chengliang Li, Yong Zhang
Federated learning is an emerging technique for training models from decentralized data sets.
1 code implementation • 26 Jan 2022 • Zhenan Fan, Huang Fang, Michael P. Friedlander
We study the federated optimization problem from a dual perspective and propose a new algorithm termed federated dual coordinate descent (FedDCD), which is based on a type of coordinate descent method developed by Necora et al.[Journal of Optimization Theory and Applications, 2017].
no code implementations • 7 Jan 2022 • Zhenan Fan, Huang Fang, Zirui Zhou, Jian Pei, Michael P. Friedlander, Yong Zhang
We show that VerFedSV not only satisfies many desirable properties for fairness but is also efficient to compute, and can be adapted to both synchronous and asynchronous vertical federated learning algorithms.
no code implementations • 19 Sep 2021 • Zhenan Fan, Huang Fang, Zirui Zhou, Jian Pei, Michael P. Friedlander, Changxin Liu, Yong Zhang
The success of federated learning depends largely on the participation of data owners.
1 code implementation • 17 Sep 2021 • Changxin Liu, Zhenan Fan, Zirui Zhou, Yang Shi, Jian Pei, Lingyang Chu, Yong Zhang
To solve it in a federated and privacy-preserving manner, we consider the equivalent dual form of the problem and develop an asynchronous gradient coordinate-descent ascent algorithm, where some active data parties perform multiple parallelized local updates per communication round to effectively reduce the number of communication rounds.
no code implementations • ICLR 2021 • Huang Fang, Zhenan Fan, Michael Friedlander
We prove that SSGD converges, respectively, with rates $O(1/\epsilon)$ and $O(\log(1/\epsilon))$ for convex and strongly-convex objectives when interpolation holds.
1 code implementation • 14 Oct 2020 • Zhenan Fan, Halyun Jeong, Babhru Joshi, Michael P. Friedlander
The signal demixing problem seeks to separate a superposition of multiple signals into its constituent components.