Research Interests

My research interests include machine learning theory; probabilistic graphical models; high-dimensional signal and information processing; and physics-inspired optimization algorithms.

Specifically, I’m focusing on the following problems.

1. Theoretical aspects of machine learning with a special interest in the interdisciplinary field between high-dimensional statistics and statistical physics;

2. Online learning and continuous learning;

3. Graph neural networks and probabilistic graphical models.

Biosketch

I received my Ph.D. degree in Theoretical Physics from the Institute of Theoretical Physics, Chinese Academy of Science, Beijing, China, in 2015. I then joined the Paulson School of Engineering and Applied Sciences at Harvard University, first as a Postdoctoral Fellow (Feb. 2015—Jan. 2018) and as a Research Associate (Feb. 2018—Aug. 2019). I won the Best Student Paper Award at the IEEE GlobalSIP Conference in 2014.

Publications

Conference:

[C.7] Chuang Wang, Hong Hu, Yue M. Lu, A Solvable High-Dimensional Model of GAN, Advances in Neural Information Processing Systems (NeurIPS), 2019

[C.6] Chuang Wang, Yue M. Lu, The scaling limit of high-dimensional online independent component analysis, Advances in Neural Information Processing Systems (NIPS), 2017 (Spotlight talk)

[C.5] Chuang Wang, Yonina C. Eldar and Yue M. Lu, Subspace estimation from incomplete observations: a precise high-dimensional analysis, Signal Processing with Adaptive Sparse Structured Representations (SPARS), Lisbon, Portugal, 2017 (Oral talk)

[C.4] Chuang Wang, Yue M. Lu, Online learning for sparse PCA in high dimensions: exact dynamics and phase transitions, 2016 IEEE Information Theory Workshop (ITW), 186-190, 2016

[C.3] Chuang Wang, A. Agaskar and Yue M. Lu, "Randomized Kaczmarz algorithm for inconsistent linear systems: an exact MSE analysis," International Conference on Sampling Theory and Applications (SampTA), Washington, DC, 2015, pp. 498-502.

[C.2] A. Agaskar, Chuang Wang, Yue M. Lu, Randomized Kaczmarz algorithms: Exact MSE analysis and optimal sampling probabilities, IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2014 (Best Student Award Paper)

[C.1] Chuang Wang, Haijun Zhou, Simplifying generalized belief propagation on redundant region graphs, Journal of Physics: Conference Series, 473, 012004 (2013)

Journal:

[J.8] Chuang Wang, Yue M. Lu, The scaling limit of high-dimensional online independent component analysis, Journal of Statistical Mechanics: Theory and Experiment, 2019 (accepted, JCR Q1)

[J.7] Chuang Wang, Yonina C. Eldar, Yue M. Lu, Subspace Estimation from Incomplete Observations: A High-Dimensional Analysis, IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 6, pp. 1240-1252, 2018 (JCR Q1)

[J.6] Chuang Wang, Jonathan Mattingly, Yue M. Lu, Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA, 2017, arXiv:1712.04332 (Preprint)

[J.5] G. D. Ferraro, Chuang Wang, Haijun Zhou, E. Aurell, On one-step replica symmetry breaking in the Edwards-Anderson spin glass model, Journal of Statistical Mechanics: Theory and Experiment, vol.7, pp.073305 (JCR Q1)

[J.4] Chuang Wang, Shaomeng Qin, Haijun Zhou, Topologically invariant tensor renormalization group method for the Edwards-Anderson spin glasses model, Physical Review B 90, vol.17, pp. 174201, 2014 (JCR Q1)

[J.3] Haijun Zhou, Chuang Wang, Region graph partition function expansion and approximate free energy landscapes: Theory and some numerical results, Journal of Statistical Physics, vol. 148, pp. 513, 2012 (JCR Q2)

[J.2] Haijun Zhou, Chuang Wang, Zedong Bi, Jinqing Xiao, Partition function expansion on region graphs and message-passing equations, Journal of Statistical Mechanics: Theory and Experiment, vol.12., pp. L12001 (JCR Q1)

[J.1] Haijun Zhou, Chuang Wang, Ground-state configuration space heterogeneity of random finite-connectivity spin glasses and random constraint satisfaction problems, Journal of Statistical Mechanics: Theory and Experiment, vol 10, pp. P10010, 2010 (JCR Q1)