Haozhu Wang's webpage

Haozhu Wang

I am a Machine Learning Scientist at 3M. I earned my Ph.D. in Electrical and Computer Engieering from EECS Department at University of Michigan, where I was advised by Prof. L. Jay Guo. My research focuses on reinforcement learning, meta-learning, and generative models. On the application side, I collaborate with domain experts to solve challenging problems in physical sciences and healthcare. My long-term research goal is to create ML systems that can assist human experts in scientific discoveries and innovations. Previously, I received my B.Eng. in Optoelectronics from a joint program at Tianjin University and Nankai University.

I always enjoy collaborating with aspiring researchers. Please feel free to send me an email if you want to discuss about research ideas.

Email / CV / Google Scholar / GitHub / Twitter / LinkedIn / Blog

News

[Jan-2022] I defended my thesis titled Learning to Optimize: Applications in Physical Designs and Manufacturing on Jan 14th, 2022.

[Sep-2021] I will graduate in Jan 2022 and join 3M AI Lab as a Machine Learning Scientist.

	NEUTRON: Neural Particle Swarm Optimization for Material-Aware Inverse Design of Structural Color Haozhu Wang, L. Jay Guo Under review, 2022 preprint/ code We propose a hybrid machine learning and optimization method that combines mixture density networks and particle swarm optimization for accurate and efficient structural color inverse design.
	Benchmarking Deep Learning-based Models on Nanophotonic Inverse Design Problems Taigao Ma, Mustafa Tobah, Haozhu Wang* , L. Jay Guo* Opto-Electronic Science, 2022 (*: correspondence) link We provide extensive benchmarking results on accuracy, diversity, robustness for commonly used deep learning models in nanophotonic inverse designs. The findings can help researchers select models that best suit their design problems.
	An Analytical Method for Evaluating the Robustness of Photonic Integrated Circuits Hanfa Song, Haozhu Wang , Vien Van Journal of Lightwave Technology, 2022 link Derived a bound for evaluating how fabrication errors affect the performance of photonic integrated circuits. The results were verified by a numerical apporach based on genetic algorithms.
	Automated Optical Multi-layer Design via Deep Reinforcement Learning Haozhu Wang , Zeyu Zheng, Chengang Ji, L. Jay Guo Machine Learning: Science and Technology, 2021 PDF/ code/ abridged NeurIPS workshop version/ Training a novel sequence generation network with Proximal Policy Optimization for automatically discovering near-optimal optical designs.
	COVID-19 Risk Scoring in Los Angeles County Litian Zhou, Wenxue Li, Zhangxing Bian, Yuxuan Cao, Xinyu Li, Weixiao Wang, Zixian Ma Junhwan Kim, Zijin Chu, Yuxi Xie, Yueze Song, Chaoyi Wang, Ruopeng Wang, Linh Tran Haozhu Wang, L. Jay Guo RMDS COVID-19 Challenge, 2020 (*: correspondence) report Apply LSTM and LR models for spatio-temporal COVID-19 risk prediction.
	Return to Work After Injury: A Sequential Prediction & Decision Problem Erkin Ötleş* Haozhu Wang , Suyanpeng Zhang, Brian Denton, Jenna Wiens, Jon Seymour Machinet Learning for Healthcare (clinical abstract), 2019 (: equal contribution) report Apply Q-learning to insurance claim data to learn near-optimal dynamic treatment regimes.
	Learning Credible Models Jiaxuan Wang, Jeeheh Oh, Haozhu Wang , Jenna Wiens KDD, 2018 paper/ code Expert-yielded-estimates regularizer for incorporating expert knowledge into linear models.
	Learning to Share: Simultaneous Parameter Tying and Sparsification in Deep Learning Dejiao Zhang, Haozhu Wang* , Mario A.T. Figueiredo, Laura Balzano ICLR, 2018 (: equal contribution) paper/ code Group-ordered-weighted lasso (GrOWL) for deep model compression.
	Surface Plasmon Polariton Laser based on a Metallic Trench Fabry-Perot Resonator Wenqi Zhu, Ting Xu, Haozhu Wang , Cheng Zhang, Parag B. Deotare, Amit Agrawal, Henri J. Lezec Science Advances, 2017 paper Surface plasmon polariton laser with a novel device structure.
	Single-Photon Imager based on a Superconducting Nanowire Delay Line Qing-Yuan Zhao, Di Zhu, Niccolò Calandri, Andrew E. Dane, Adam N. McCaughan, Francesco Bellei, Hao-Zhu Wang, Daniel F. Santavicca, Karl K. Berggren Nature Photonics, 2017 paper Superconduting nanowire single photon detector as a highly-sensitive imager.

Teaching

EECS 442 Computer Vision (F20), Prof. Andrew Owens
Graduate Student Instructor

EECS 504 Fundations of Computer Vision (W20), Prof. Andrew Owens
Graduate Student Instructor

EECS 545 Machine Learning (F17), Prof. Mert Pilanci
Graduate Student Instructor

Service

Conference review:	ICML'22, ICLR'22, NeurIPS'20-21, AMIA'20-21, MLHC'18-21
Journal review:	Journal of Physics Communications, AIP Advances
Workshop review:	NeurIPS'20-21 Meta-Learning Workshop, NeurIPS'21 Machine Learning and the Physical Sciences Workshop

Useful Links

There is nothing as practical as a good theory. — Kurt Lewin

The source code of this website is from Jon Barron.

(last update: Jan 2022)