AI+Healthcare, AI theory, Applied Category Theory
I work on AI+healthcare, AI theory and applied category theory. I want to build a new healthcare system guided by category theory.
In AI + healthcare, I work on the following three directions:
1. Traditional Chinese Medicine (TCM) Assisted Diagnosis System: according to clinical data, our system can provide prescriptions similar or identical to the experienced TCM practitioners in many cases.
2. Pulse Diagnosis: based on pulse information, we infer the patient's physical and mental state, including insomnia, anxiety, bloating, fatigue, etc.
3. Drug Discovery: unlike the approach of targeted drugs, we combine TCM theory with category theory, aim to find compound prescriptions for certain syndromes, with the help of foundation models.
The advancement of AI + healthcare is inseparable from mathematics. To better build an assisted diagnosis system, I learned category theory. I found that it can not only be used to analyze and understand complex systems but also to characterize the power of foundation models and design new algorithms. Therefore, I am also very interested in the applications of category theory in AI.
I did my PhD at Cornell University, advised by Professor Robert Kleinberg. After graduation, I spent one year at MIT as a postdoc. I did my undergraduate at Peking University, and I was born in Changzhou.
My CV and Google Scholar page.
On the power of foundation models
Yang Yuan ICML 2023
《孟子·告子下》:有诸内,必形诸外。
《黄帝内经·灵枢·外揣》:司外揣内,司内揣外。
Contrastive learning is spectral clustering on similarity graph
Zhiquan Tan, Yifan Zhang, Jingqin Yang, Yang Yuan ICLR 2024
Category theory for AI in single dimensional case.
Trade-off between efficiency and consistency for removal-based explanations
Yifan Zhang, Haowei He, Zhiquan Tan, Yang Yuan NeurIPS 2023
Impossible Trinity of removal-based explanations.
Publications
Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts,
Yifan Zhang, Yifan Luo, Yang Yuan, Andrew C Yao,
ACL 2025 Findings.
Hierarchical Attention Generates Better Proofs,
Jianlong Chen, Chao Li, Yang Yuan, Andrew C Yao,
ACL 2025 Main.
CatCode: A Comprehensive Evaluation Framework for LLMs On the Mixture of Code and Text,
Zhenru Lin, Yiqun Yao, Yang Yuan,
COLM 2024.
Matrix Information Theory for Self-Supervised Learning,
Yifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan,
ICML 2024.
Information Flow in Self-Supervised Learning,
Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang,
ICML 2024.
Contrastive Learning is Spectral Clustering on Similarity Graph,
Zhiquan Tan, Yifan Zhang, Jingqin Yang, Yang Yuan,
ICLR 2024.
Trade-off Between Efficiency and Consistency for Removal-based Explanations,
Yifan Zhang, Haowei He, Zhiquan Tan, Yang Yuan,
NeurIPS 2023.
Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression,
Jing Xu, Jiaye Teng, Yang Yuan, Andrew C. Yao,
NeurIPS 2023.
On the Power of Foundation Models,
Yang Yuan,
ICML 2023. [arxiv]
On Uni-Modal Feature Learning in Supervised Multi-Modal Learning,
Chenzhuang Du, Jiaye Teng, Tingle Li, Yichen Liu, Tianyuan Yuan, Yue Wang, Yang Yuan, Hang Zhao,
ICML 2023.
Finding Generalization Measures by Contrasting Signal and Noise,
Jiaye Teng, Bohang Zhang, Ruichen Li, Haowei He, Yequan Wang, Yan Tian, Yang Yuan,
ICML 2023.
Predictive Inference with Feature Conformal Prediction,
Jiaye Teng*, Chuan Wen*, Dinghuai Zhang*, Yoshua Bengio, Yang Gao, Yang Yuan,
ICLR 2023. [arxiv]
Towards Understanding Generalization via Decomposing Excess Risk Dynamics,
Jiaye Teng, Jianhao Ma, Yang Yuan,
ICLR 2022. [arxiv]
T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP,
Jiaye Teng, Zeren Tan, Yang Yuan,
ICML 2021. [arxiv]
A Stratified Approach to Robustness for Randomly Smoothed Classifiers,
Guang-He Lee, Yang Yuan, Shiyu Chang, Tommi S. Jaakkola,
NeurIPS 2019. [paper]
Learning-Based Low-Rank Approximations,
Piotr Indyk, Ali Vakilian, Yang Yuan, [α-β ordering]
NeurIPS 2019. [arxiv]
Asymmetric Valleys: Beyond Sharp and Flat Local Minima,
Haowei He, Gao Huang, Yang Yuan,
NeurIPS 2019 (spotlight). [arxiv]
Expanding Holographic Embeddings for Knowledge Completion,
Yexiang Xue, Yang Yuan, Zhitian Xu, Ashish Sabharwal,
NIPS 2018. [paper]
An Alternative View: When Does SGD Escape Local Minima?
Robert Kleinberg, Yuanzhi Li, Yang Yuan, [α-β ordering]
ICML 2018. [arxiv]
Hyperparameter Optimization: A Spectral Approach,
Elad Hazan, Adam Klivans, Yang Yuan, [α-β ordering]
ICLR 2018. Previously appeared in NIPS DLTP Workshop 2017 (oral) [arxiv] [github]
YATES: Rapid Prototyping for Traffic Engineering Systems,
Praveen Kumar, Chris Yu, Yang Yuan, Nate Foster, Robert Kleinberg, Robert Soulé,
SOSR 2018. [paper]
Semi-Oblivious Traffic Engineering: The Road Not Taken,
Praveen Kumar, Yang Yuan, Chris Yu, Nate Foster, Robert Kleinberg, Petr Lapukhov, Chiun Lin Lim, Robert Soulé,
NSDI 2018. [arxiv]
Convergence Analysis of Two-layer Neural Networks with ReLU Activation,
Yuanzhi Li, Yang Yuan, [α-β ordering]
NIPS 2017. [arxiv]
Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters,
Zeyuan Allen-Zhu*, Yang Yuan*, Karthik Sridharan, [* denotes equal contribution]
NIPS 2016. [arxiv]
Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling,
Zeyuan Allen-Zhu, Zheng Qu, Peter Richtárik, Yang Yuan, [α-β ordering]
ICML 2016. [arxiv]
Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives,
Zeyuan Allen-Zhu, Yang Yuan, [α-β ordering]
ICML 2016. [arxiv] [Code for SVRG++ and other VR algorithms in Scala]
Optimization Algorithms for Computational Geometry,
Zeyuan Allen-Zhu, Zhenyu Liao, Yang Yuan, [α-β ordering]
ICALP 2016. [arxiv]
Simultaneous Nearest Neighbor Search,
Piotr Indyk, Robert Kleinberg, Sepideh Mahabadi, Yang Yuan, [α-β ordering]
SoCG 2016. [arxiv]
Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Arms,
Wei Chen, Yajun Wang, Yang Yuan, Qinshi Wang
JMLR 2016. [arxiv]
Conference version:
Combinatorial Multi-Armed Bandit: General Framework, Results and Applications,
Wei Chen, Yajun Wang, Yang Yuan [α-β ordering]
ICML 2013. [pdf]
Escaping From Saddle Points – Online Stochastic Gradient for Tensor Decomposition,
Rong Ge, Furong Huang, Chi Jin, Yang Yuan, [α-β ordering]
COLT 2015. [arxiv]
Optimal Auctions vs. Anonymous Pricing,
Saeed Alaei, Jason Hartline, Rad Niazadeh, Emmanouil Pountourakis, Yang Yuan, [α-β ordering]
Games and Economic Behavior, Volume 118, November 2019, Pages 494-510.
Conference version: FOCS 2015. [arxiv]
Simple and Near-Optimal Mechanisms for Market Intermediation,
Rad Niazadeh, Yang Yuan, Robert Kleinberg,
WINE 2014. [arxiv]
On the Ratio of Revenue to Welfare in Single-Parameter Mechanism Design,
Robert Kleinberg, Yang Yuan, [α-β ordering]
EC 2013. [arxiv]
Boreas: An Accurate and Scalable Token-based Approach to Code Clone Detection,
Yang Yuan, Yao Guo,
ASE 2012. [pdf]
A Fast Parallel Branch and Bound Algorithm for Treewidth,
Yang Yuan,
ICTAI 2011. [pdf] [special thanks]
Manuscript
An empirical study on evaluation metrics of generative adversarial networks,
Qiantong Xu, Gao Huang, Yang Yuan, Chuan Guo, Yu Sun, Felix Wu, Kilian Weinberger,
Manuscript 2018. [arxiv]
Students
PhD Students
Haowei He (2019-2024, afterwards: China Telecom)
Jiaye Teng (2020-2024, afterwards: Assistant Professor at Shanghai University of Finance and Economics)
Jingqin Yang (2021-)
Zhenru Lin (2022-)
Yifan Luo (2024-)
Kangping Xu (Co-advised with Prof. Andrew Yao, 2024-)
Master Student
Yifan Zhang (2021-)
Shuxin Zhang (2019-2022, afterwards: PhD at Peking University)
Postdoc
Chao Li (2021-2023, afterwards: Shanghai Qizhi Institute)
Teaching
Machine Learning (Fall 2019-2024)
Type-safe Modern System Practice (Summer 2022-2024)
Introduction to AI (Fall 2019-2020)
AI+X (Fall 2021)
AI Research Practice (Fall 2022)