Research Interests
My research interests are as follows.
- Randomized linear algebra
- Large-scale optimization
- Machine learning
2024 papers
AutoML for Large Capacity Modeling of Meta's Ranking Systems Hang Yin, Kuang-Hung Liu, Mengying Sun, Yuxin Chen, Buyun Zhang, Jiang Liu, Vivek Sehgal, Rudresh Rajnikant Panchal, Eugen Hotaj, Xi Liu, Daifeng Guo, Jamey Zhang, Zhou Wang, Shali Jiang, Huayu Li, Zhengxing Chen, Wen-Yen Chen, Jiyan Yang, Wei Wen International World Wide Web Conferences (WWW), 2024. [arxiv]
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen International World Wide Web Conferences (WWW), 2024. [arxiv]
2023 papers
Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking Xuewei Wang, Qiang Jin, Shengyu Huang, Min Zhang, Xi Liu, Zhengli Zhao, Yukun Chen, Zhengyu Zhang, Jiyan Yang, Ellie Wen, Sagar Chordia, Wenlin Chen, Qin Huang ADKDD, 2023. [paper]
AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations Danwei Li, Zhengyu Zhang, Siyang Yuan, Mingze Gao, Weilin Zhang, Chaofei Yang, Xi Liu, Jiyan Yang International Conference on Knowledge Discovery and Data Mining (KDD), 2023. [paper]
2022 papers
Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models Dheevatsa Mudigere, et al. International Symposium on Computer Architecture (ISCA), 2022. [arxiv]
DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction Buyun Zhang, et al. Workshop on Deep Learning Practice and Theory for High-Dimensional Sparse and Imbalanced Data with KDD (DLP-KDD), 2022. [paper]
2021 papers
Hierarchical Training: Scaling Deep Recommendation Models on Large CPU Clusters Yuzhen Huang, Xiaohan Wei, Xing Wang, Jiyan Yang, Bor-Yiing Su, Shivam Bharuka, Dhruv Choudhary, Zewei Jiang, Hai Zheng, Jack Langman International Conference on Knowledge Discovery and Data Mining (KDD), 2021. [paper]
Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark C. Jeffrey, Vikram Saraph, Bor-Yiing Su, Caroline Trippel, Jiyan Yang, Mike Rabbat, Brandon Lucia, Carole-Jean Wu Conference on Machine Learning and Systems (MLSys), 2021. [paper] [arxiv]
Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems Antonio Ginart, Maxim Naumov, Dheevatsa Mudigere, Jiyan Yang, James Zou IEEE International Symposium on Information Theory (ISIT), 2021. [paper] [arxiv]
2020 papers
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems Hao-Jun Michael Shi, Dheevatsa Mudigere, Maxim Naumov, Jiyan Yang International Conference on Knowledge Discovery and Data Mining (KDD), 2020. [arxiv]
Towards Automated Neural Architecture Discovery for Click-Through Rate Prediction Qingquan Song, Dehua Cheng, Eric Zhou, Jiyan Yang, Yuandong Tian, Xia Hu International Conference on Knowledge Discovery and Data Mining (KDD), 2020. [arxiv]
Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems Maxim Naumov, John Kim, Dheevatsa Mudigere, Srinivas Sridharan, Xiaodong Wang, Whitney Zhao, Serhat Yilmaz, Changkyu Kim, Hector Yuen, Mustafa Ozdal, Krishnakumar Nair, Isabel Gao, Bor-Yiing Su, Jiyan Yang, Mikhail Smelyanskiy arXiv preprint, 2020. [arxiv]
ShadowSync: Performing Synchronization in the Background for Highly Scalable Distributed Training Qinqing Zheng, Bor-Yiing Su, Jiyan Yang, Alisson Azzolini, Qiang Wu, Ou Jin, Shri Karandikar, Hagay Lupesko, Liang Xiong, Eric Zhou arXiv preprint, 2020. [arxiv]
2019 Papers
Post-Training 4-bit Quantization on Embedding Tables Hui Guan, Andrey Malevich, Jiyan Yang, Jongsoo Park, Hector Yuen Workshop on Systems for ML and Open Source Software at NeurIPS, 2019. [arxiv]
A Study of BFLOAT16 for Deep Learning Training Dhiraj Kalamkar, et al. arXiv preprint, 2019. [arxiv]
2018 Papers
Training with Low-precision Embedding Tables Jian Zhang, Jiyan Yang, Hector Yuen Workshop on Systems for ML and Open Source Software at NeurIPS, 2018. [paper]
Weighted SGD for Lp Regression with Randomized Preconditioning Jiyan Yang, Yin-Lam Chow, Christopher Ré, and Michael W. Mahoney J. Machine Learning Research, 18(211), 1-43, 2018. [paper] [arXiv] [slides]
2016 Papers
Feature-distributed Sparse Regression: A Screen-and-clean Approach Jiyan Yang, Michael W. Mahoney, Michael Saunders, and Yuekai Sun Neural Information Processing Systems (NIPS), 2016. [paper]
Sub-sampled Newton Methods with Non-uniform Sampling Peng Xu, Jiyan Yang, Farbod Roosta-Khorasani, Christopher Ré, and Michael W. Mahoney Neural Information Processing Systems (NIPS), 2016. [paper] [arXiv (long version)] [slides]
Matrix Factorization at Scale: a Comparison of Scientific Data Analytics in Spark and C+MPI Using Three Case Studies Alex Gittens, et al. IEEE International Conference on Big Data (IEEE BigData), 2016. [paper] [arXiv] [codes]
Weighted SGD for Lp Regression with Randomized Preconditioning Jiyan Yang, Yin-Lam Chow, Christopher Ré, and Michael W. Mahoney ACM-SIAM Symposium on Discrete Algorithms (SODA), 2016. [paper] [arXiv (long version)] [slides]
Implementing Randomized Matrix Algorithms in Parallel and Distributed Environments Jiyan Yang, Xiangrui Meng, and Michael W. Mahoney Proceedings of the IEEE, 104(1), 58-92, 2016. [paper] [arXiv] [codes] [slides]
Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels Haim Avron*, Vikas Sindhwani*, Jiyan Yang*, and Michael W. Mahoney *alphabetical authorship order. J. Machine Learning Research, 17(120), 1-38, 2016. [paper] [arXiv] [codes] [slides]
Distributed Online Modified Greedy Algorithm for Networked Storage Operation under Uncertainty Junjie Qin, Yin-Lam Chow, Jiyan Yang, and Ram Rajagopal IEEE Transactions on Smart Grid, 7(2), 1106-1118, 2016. [paper] [arXiv]
Online Modified Greedy Algorithm for Storage Control under Uncertainty Junjie Qin, Yin-Lam Chow, Jiyan Yang, and Ram Rajagopal IEEE Transactions on Power Systems, 31(3), 1729-1743, 2016. [paper] [arXiv]
A Multi-platform Evaluation of the Randomized CX Low-rank Matrix Factorization in Spark Alex Gittens et al. International Workshop on Parallel and Distributed Computing for Large Scale Machine Learning and Big Data Analytics (ParLearning), at IPDPS, 2016. [paper]
2015 Papers
Identifying Important Ions and Positions in Mass Spectrometry Imaging Data Using CUR Matrix Decompositions Jiyan Yang, Oliver Rübel, Prabhat, Michael W. Mahoney, and Ben P. Bowen Analytical Chemistry, 87(9), 4658-4666, 2015. [paper] [codes]
Tensor Machines for Learning Target-specific Polynomial Features Jiyan Yang and Alex Gittens arXiv preprint, 2015. [arXiv] [codes]
2014 Papers
Modeling and Online Control of Generalized Energy Storage Networks Junjie Qin, Yin-Lam Chow, Jiyan Yang, and Ram Rajagopal International Conference on Future Energy Systems (ACM e-Energy), 2014. [paper] [arXiv]
Random Laplace Feature Maps for Semigroup Kernels on Histograms Jiyan Yang, Vikas Sindhwani, Quanfu Fan, Haim Avron, and Michael W. Mahoney IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014. [paper]
Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels Jiyan Yang*, Vikas Sindhwani*, Haim Avron*, and Michael W. Mahoney * indicates equal contribution. International Conference on Machine Learning (ICML), 2014. [paper] [extended version] [arXiv (long version)] [codes] [slides]
Quantile Regression for Large-scale Applications
Jiyan Yang, Xiangrui Meng, and Michael W. Mahoney
SIAM J. Scientific Computing, 36(5), S78-S110, 2014.
[paper]
[arXiv]
[codes]
[slides]
2013 Papers
Quantile Regression for Large-scale Applications Jiyan Yang, Xiangrui Meng, and Michael W. Mahoney International Conference on Machine Learning (ICML), 2013. [paper] [arXiv (long version)] [codes] [slides]
Dissertation
Randomized Linear Algebra For Large-scale Data Applications [thesis]
Talks
Sub-sampled Newton Methods with Non-uniform Sampling. PCMI, 2016. [slides]
Weighted SGD for Lp Regression with Randomized Preconditioning. SODA, 2016. [slides]
Implementing Randomized Matrix Algorithms in Parallel and Distributed Environmentsi. INFORMS, 2015. [slides]
Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels. ICML, 2014. [slides]
Quantile Regression for Large-scale Applications. ICML, 2013. [slides]