no code implementations • 16 Mar 2023 • Jiang Hu, Kangkang Deng, Na Li, Quanzheng Li
With a computationally efficient approximation of the second-order information, natural gradient methods have been successful in solving large-scale structured optimization problems.
no code implementations • 15 Jul 2022 • Jiang Hu, Ruicheng Ao, Anthony Man-Cho So, MingHan Yang, Zaiwen Wen
Moreover, we show that if the loss function satisfies certain convexity and smoothness conditions and the input-output map satisfies a Riemannian Jacobian stability condition, then our proposed method enjoys a local linear -- or, under the Lipschitz continuity of the Riemannian Jacobian of the input-output map, even quadratic -- rate of convergence.
no code implementations • 30 Mar 2022 • Jingyu Pan, Chen-Chia Chang, Zhiyao Xie, Ang Li, Minxue Tang, Tunhou Zhang, Jiang Hu, Yiran Chen
To further strengthen the results, we co-design a customized ML model FLNet and its personalization under the decentralized training scenario.
no code implementations • 19 Feb 2021 • Lang Feng, Jiayi Huang, Jeff Huang, Jiang Hu
Data-Flow Integrity (DFI) is a well-known approach to effectively detecting a wide range of software attacks.
no code implementations • 3 Dec 2020 • Chen-Chia Chang, Jingyu Pan, Tunhou Zhang, Zhiyao Xie, Jiang Hu, Weiyi Qi, Chun-Wei Lin, Rongjian Liang, Joydeep Mitra, Elias Fallon, Yiran Chen
The rise of machine learning technology inspires a boom of its applications in electronic design automation (EDA) and helps improve the degree of automation in chip designs.
no code implementations • 27 Nov 2020 • Zhiyao Xie, Rongjian Liang, Xiaoqing Xu, Jiang Hu, Yixiao Duan, Yiran Chen
Net length is a key proxy metric for optimizing timing and power across various stages of a standard digital design flow.
no code implementations • 26 Nov 2020 • Zhiyao Xie, Hai Li, Xiaoqing Xu, Jiang Hu, Yiran Chen
IR drop constraint is a fundamental requirement enforced in almost all chip designs.
no code implementations • 26 Nov 2020 • Zhiyao Xie, Guan-Qi Fang, Yu-Hung Huang, Haoxing Ren, Yanqing Zhang, Brucek Khailany, Shao-Yun Fang, Jiang Hu, Yiran Chen, Erick Carvajal Barboza
Experimental results on benchmark circuits show that our approach achieves 25% improvement in design quality or 37% reduction in sampling cost compared to random forest method, which is the kernel of a highly cited previous work.
no code implementations • 26 Nov 2020 • Zhiyao Xie, Haoxing Ren, Brucek Khailany, Ye Sheng, Santosh Santosh, Jiang Hu, Yiran Chen
Moreover, the proposed CNN model is general and transferable to different designs.
no code implementations • 17 Nov 2020 • Erick Carvajal Barboza, Sara Jacob, Mahesh Ketkar, Michael Kishinevsky, Paul Gratz, Jiang Hu
Design bugs that affect processor performance rather than its functionality are especially difficult to catch, particularly in new microarchitectures.
1 code implementation • 3 Sep 2018 • Jiang Hu, Bo Jiang, Lin Lin, Zaiwen Wen, Yaxiang Yuan
In particular, we are interested in applications that the Euclidean Hessian itself consists of a computational cheap part and a significantly expensive part.
Optimization and Control
2 code implementations • 7 Aug 2017 • Jiang Hu, Andre Milzarek, Zaiwen Wen, Yaxiang Yuan
Optimization on Riemannian manifolds widely arises in eigenvalue computation, density functional theory, Bose-Einstein condensates, low rank nearest correlation, image registration, and signal processing, etc.
Optimization and Control