Hao Wu is a PhD student in the Machine Learning program at Northeastern University, advised by Jan-Willem van de Meent. Hao’s current research is focused on variational inference, probabilistic programming, and machine learning. Prior to joining Northeastern, Hao researched computational user behavior modeling, time-dependent differential equations, and large linear systems. Hao works on mathematical and statistical models to solve abstract and practical problems. Hao earned his Bachelor’s of Science degree from Sichuan University in China, his Master’s in Applied Mathematics from the University of Washington, and his Master’s in Computer Science from the University of Virginia.
Currently I focus on research work in variational inference, probabilistic programming, and machine learning. Before coming here, my main works included computational user behavior modeling, time-dependent differential equations, and large linear systems.
I have been working on mathematical and statistical models to solve abstract and practical problems. Through my previous research I became very interested in improving learning and prediction, especially how to represent uncertainty and dynamics.
I am trying to design better variational autoencoder framework for sampling and unsupervised learning.
Though deep learning methods have impressive scalability, the data-driven model still needs improvement when it deals with uncertainty, unobservable information, and dynamic systems.
I would like to continue my research work after my PhD program.
I grew up in my hometown in China, and since 2014 I have studied in Seattle for one year and then in Charlottesville for one and a half years.
I earned my undergraduate degree from Sichuan University in China.
Hao Wu is a PhD student in the Machine Learning program at Northeastern University, advised by Jan-Willem van de Meent. Hao’s current research is focused on variational inference, probabilistic programming, and machine learning. Prior to joining Northeastern, Hao researched computational user behavior modeling, time-dependent differential equations, and large linear systems. Hao works on mathematical and statistical models to solve abstract and practical problems. Hao earned his Bachelor’s of Science degree from Sichuan University in China, his Master’s in Applied Mathematics from the University of Washington, and his Master’s in Computer Science from the University of Virginia.
Currently I focus on research work in variational inference, probabilistic programming, and machine learning. Before coming here, my main works included computational user behavior modeling, time-dependent differential equations, and large linear systems.
I have been working on mathematical and statistical models to solve abstract and practical problems. Through my previous research I became very interested in improving learning and prediction, especially how to represent uncertainty and dynamics.
I am trying to design better variational autoencoder framework for sampling and unsupervised learning.
Though deep learning methods have impressive scalability, the data-driven model still needs improvement when it deals with uncertainty, unobservable information, and dynamic systems.
I would like to continue my research work after my PhD program.
I grew up in my hometown in China, and since 2014 I have studied in Seattle for one year and then in Charlottesville for one and a half years.
I earned my undergraduate degree from Sichuan University in China.
