Guanyang Wang   王冠扬

Guanyang Wang Assistant Professor Department of Statistics Rutgers University, New Brunswick Contact Department of Statistics Office 453, Hill Center 110 Frelinghuysen Road Piscataway, NJ 08854 Email: guanyang.wang [at] rutgers [dot] edu

About me

Welcome! I am an assistant professor in the Department of Statistics at Rutgers University, New Brunswick.

My research primarily focuses on Markov Chain Monte Carlo (MCMC) techniques, general Monte Carlo methods, and probability. Recently I am also very interested in quantum computing. Feel free to contact me if you would like to chat about interests we may share. My research is partially supported by NSF DMS-2210849 and an Adobe Data Science Research Award . Thank you!

I received my Ph.D. in Mathematics (Ph.D. minor in Statistics) from Stanford University in August 2020, advised by Prof. Persi Diaconis. Prior to that, I received my B.S. with Honors in Mathematics from University of Science and Technology of China (USTC) in Jun 2015.

My Erdős number is 2 ( [1] , [2] , and [3]. )

People

• Yasa Syed (Statistics, fifth year Ph.D. student)

• Wei Yuan (Statistics, fourth year Ph.D. student)

• Budhaditya Halder (Statistics, fourth year Ph.D. student)

• Tianze Wang (Statistics, third year Ph.D. student)

• Yuchen Wei (Mathematics, sixth year Ph.D. student)

Recent News

• New paper Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach with Wei Yuan is on arxiv (Jun, 2024).

• New paper When are Unbiased Monte Carlo Estimators More Preferable than Biased Ones? with Jose Blanchet, and Peter Glynn is on arxiv (Apr, 2024).

• New paper Differentially Private Range Queries with Correlated Input Perturbation with Prathamesh Dharangutte, Jie Gao , and Ruobin Gong is on arxiv (Feb, 2024).

• New paper Quadratic Speed-up in Infinite Variance Quantum Monte Carlo with Jose Blanchet and Mario Szegedy is on arxiv (Jan, 2024).

• Paper Repeated averages on graphs with Ramis Movassagh and Mario Szegedy accepted in the Annals of Applied Probability (AoAP) (Jan, 2024).

• New paper Spectral gap bounds for reversible hybrid Gibbs chains with Qian Qin and Nianqiao Ju is on arxiv (Dec, 2023).

• Excited to receive the Blackwell-Rosenbluth Award by j-ISBA (Nov, 2023)!

• Paper Prediction and Design of Protease Enzyme Specificity Using a Structure-Aware Graph Convolutional Network with Changpeng Lu, Joseph H. Lubin, Vidur S. Sarma, Samuel Z. Stentz, Sijian Wang, and Sagar D. Khare accepted in the Proceedings of the National Academy of Sciences (PNAS) (Aug, 2023).

• Paper Spectral telescope: Convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure with Qian Qin accepted in the Annals of Applied Probability (AoAP) (Jun, 2023). There is a very nice blog by Sam Power on this project.

• Paper Unbiased Multilevel Monte Carlo methods for intractable distributions: MLMC meets MCMC with Tianze Wang accepted in the Journal of Machine Learning Research (JMLR) (Jun, 2023).

Recent Works

• Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach
  Wei Yuan ^**, Guanyang Wang [arXiv]
  Submitted

• When are Unbiased Monte Carlo Estimators More Preferable than Biased Ones?
  Guanyang Wang, Jose Blanchet, Peter Glynn [arXiv]
  Submitted

• Differentially Private Range Queries with Correlated Input Perturbation
  Prathamesh Dharangutte, Jie Gao, Ruobin Gong, Guanyang Wang^* [arXiv]
  Submitted

• Quadratic Speed-up in Infinite Variance Quantum Monte Carlo
  Jose Blanchet, Mario Szegedy, Guanyang Wang^* [arXiv]
  Submitted

• Spectral gap bounds for reversible hybrid Gibbs chains
  Qian Qin, Nianqiao Ju, Guanyang Wang [arXiv]
  Submitted

• Unbiased Multilevel Monte Carlo methods for intractable distributions: MLMC meets MCMC
  Tianze Wang ^**, Guanyang Wang
  Journal of Machine Learning Research (JMLR) 2023 [arXiv] [Code] [Slides]

• Optimal randomized multilevel Monte Carlo for repeatedly nested expectations
  Yasa Syed^**, Guanyang Wang
  Conference version: International Conference on Machine Learning (ICML) 2023 [arXiv] [Code] [Slides]

• Spectral telescope: Convergence rate bounds for random-scan Gibbs samplers based on a hierarchical structure
  Qian Qin, Guanyang Wang^*
  Accepted, the Annals of Applied Probability (AoAP) 2024 [Blog by Sam] [Slides by Qian]

• Prediction and Design of Protease Enzyme Specificity Using a Structure-Aware Graph Convolutional Network
  Changpeng Lu, Joseph H. Lubin, Vidur S. Sarma, Samuel Z. Stentz, Guanyang Wang, Sijian Wang, Sagar D. Khare
  Proceedings of the National Academy of Sciences (PNAS) 2023 [bioRxiv]

• Repeated averages on graphs
  Ramis Movassagh, Mario Szegedy, Guanyang Wang^*
  Accepted, the Annals of Applied Probability (AoAP)

Miscellaneous

• Chinese Painting Generation Using Generative Adversarial Networks
  Guanyang Wang, Ying Chen, Yuan Chen
  CS231n Course Project, 2017. [Chinese Painting Dataset]

• Pattern detection in bipartite networks: a review of terminology, applications and methods
  Zachary Neal, Annabel Cadieux, Diego Garlaschelli, Nicholas J. Gotelli, Fabio Saracco, Tiziano Squartini, Shade T. Shutters, Werner Ulrich, Guanyang Wang, Giovanni Strona [arXiv]