Hongru Yang

22 papers A* 3A 2C 4Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2025 — conf
AutoFPIR: A Automatic Conversion Tool for Floating-point Program to Equivalent Intermediate Representation.
ICSIM
Yuchang Zhou, Ping Zhang, Jinchen Xu, Bei Zhou, Mengqi Cui, Hongru Yang, Liguang Ji, Jianing Zhang
2025 C conf
GATUNER:Genetic Algorithm Applied to Floating-Point Precision Tuning.
APSEC
Jianing Zhang, Jinchen Xu, Hongru Yang, Tao Zhang, Shuai Wang, Bei Zhou
2025 J jnl
PESA: error sensitivity analysis tool for floating-point computational programs.
J. Supercomput.
Mengqi Cui, Jinchen Xu, Yuchang Zhou, Hongru Yang, Liguang Ji, Bei Zhou
2025 J jnl
Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis.
J. Mach. Learn. Res.
Hongru Yang, Yingbin Liang, Xiaojie Guo, Lingfei Wu, Zhangyang Wang
2025 C conf
Scalable Detection of Floating-Point Errors via Adaptive Parallel Subdomain Search.
QRS
Zuoyan Zhang, Shihan Yuan, Hongru Yang, Jie Zhao, Jinchen Xu
2025 A* conf
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow.
ICLR
Hongru Yang, Zhangyang Wang, Jason D. Lee, Yingbin Liang
2024 A conf
Arfa: An Agile Regime-Based Floating-Point Optimization Approach for Rounding Errors.
ISSTA
Jinchen Xu, Mengqi Cui, Fei Li, Zuoyan Zhang, Hongru Yang, Bei Zhou, Jie Zhao
2024 C conf
LCOC: A Low-cost Optimizing Compiler for Large Scale Quantum Programs Towards Realistic Hardware.
ISPA
Yu Zhu, Jinchen Xu, Qing Mu, Hongru Yang, Xiaodong Ding, Qiming Du, Zheng Shan
2024 J jnl
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK.
J. Mach. Learn. Res.
Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Yingbin Liang, Zhangyang Wang
2024 A* conf
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis.
NeurIPS
Hongru Yang, Bhavya Kailkhura, Zhangyang Wang, Yingbin Liang
2024 J jnl
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis.
CoRR
Hongru Yang, Bhavya Kailkhura, Zhangyang Wang, Yingbin Liang
2023 C conf
AMPT: Automatic Mixed-Precision Tuning Based on Accuracy Gain.
APSEC
Jiangwei Hao, Yuanyuan Xia, Fei Li, Hongru Yang, Zongjiang Yi, Bei Zhou, Jianmin Pang
2023 J jnl
Convergence and Generalization of Wide Neural Networks with Large Bias.
CoRR
Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Zhangyang Wang, Yingbin Liang
2023 A* conf
Eiffel: Inferring Input Ranges of Significant Floating-point Errors via Polynomial Extrapolation.
ASE
Zuoyan Zhang, Bei Zhou, Jiangwei Hao, Hongru Yang, Mengqi Cui, Yuchang Zhou, Guanghui Song, Fei Li, Jinchen Xu, Jie Zhao
2023 A conf
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks.
AISTATS
Hongru Yang, Zhangyang Wang
2023 J jnl
Pruning Before Training May Improve Generalization, Provably.
CoRR
Hongru Yang, Yingbin Liang, Xiaojie Guo, Lingfei Wu, Zhangyang Wang
2022 J jnl
On the Neural Tangent Kernel Analysis of Randomly Pruned Wide Neural Networks.
CoRR
Hongru Yang, Zhangyang Wang
2021 J jnl
Application of multivariate statistics and 3D visualization analysis in tacit knowledge diffusion map.
Displays
Hongru Yang, Jiajun Li
2021 J jnl
Comparison of Accuracy and Scalability of Gauss-Newton and Alternating Least Squares for CANDECOMC/PARAFAC Decomposition.
SIAM J. Sci. Comput.
Navjot Singh, Linjian Ma, Hongru Yang, Edgar Solomonik
2020 J jnl
Continuous Regular Functions.
Log. Methods Comput. Sci.
Alexi Block Gorman, Philipp Hieronymi, Elliot Kaplan, Ruoyu Meng, Erik Walsberg, Zihe Wang, Ziqin Xiong, Hongru Yang
2019 J jnl
Comparison of Accuracy and Scalability of Gauss-Newton and Alternating Least Squares for CP Decomposition.
CoRR
Navjot Singh, Linjian Ma, Hongru Yang, Edgar Solomonik
2019 J jnl
Continuous Regular Functions.
CoRR
Alexi Block Gorman, Philipp Hieronymi, Elliot Kaplan, Ruoyu Meng, Erik Walsberg, Zihe Wang, Ziqin Xiong, Hongru Yang