Haozhu Wang 

I'm a Ph.D. student in EECS Department at University of Michigan, where I work on machine learning and applications to science and engineering. Previously, I received my B.Eng. in Optoelectronics from a joint program at Tianjin University and Nankai University. I visited QNN lab at MIT RLE during my last year of undergraduate study.

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  /  Twitter

I'm developing machine learning methods for speeding up scientific discoveries. Specifically, I'm intereseted in sample efficient reinforcement learning algorithms useful for real-world science and engineering applications. In the past, I've worked on model compression and ML applications in healthcare.

There is nothing more practical than a good theory. — Kurt Lewin

Training a novel sequence generation network with Proximal Policy Optimization for automatically discovering near-optimal optical designs.

Apply LSTM and LR models for spatio-temporal COVID-19 risk prediction.

Apply Q-learning to insurance claim data to learn near-optimal dynamic treatment regimes.

Expert-yielded-estimates regularizer for incorporating expert knowledge into linear models.

Group-ordered-weighted lasso (GrOWL) for deep model compression.

Surface plasmon polariton laser with a novel device structure.

Superconduting nanowire single photon detector as a highly-sensitive imager.

The source code of this website is from Jon Barron.