Prof. Huang's research focuses on non-convex optimization for spectral methods (matrix and tensor decomposition) and learning latent variable graphical models (such as latent Dirichlet allocation, mixtures of graphical models, hidden Markov models) on distributed systems with large-scale data. Some of her previous works involve distributed spectral decomposition techniques for topic modeling and mixed membership detection for large-scale networks with extension to temporally evolving networks.
She is also interested in optimization of large scale numerical algebraic operations and distributed computing systems. For instance, she worked on distributed realization of alternating minimization for tensor decomposition on the cloud.
Another thread of her research lies in computational biology and neuroscience. Generally she is interested in applying machine learning techniques to help target biological experiments.
- University of California, Irvine, Master's & Ph.D. in Machine Learning
- Zhejiang University, Bachelor of Science in Electrical Engineering & Computer Science