About

Hi! I am a second-year Ph.D. student at the Department of Computer Science, the University of Texas at Austin, where I am very fortunate to be advised by Professor Qiang Liu and Professor Nhat Ho. Before going to Austin, I was a Research Resident at VinAI Research and was a Research Assistant at Data Science Lab. I graduated from the honors program at Hanoi University of Science and Technology with a Computer Science Bachelor’s degree.

My CV is available here.

Research interests

My central research has been motivated by developing impactful, interpretable, and reliable algorithms for machine learning models. Currently, my research focuses on methods at the intersection of probabilistic modeling, deep learning and optimization, from which I aim to integrate the complementary advantages of these fields into foundation problems of modeling, inference, and learning. I am particularly excited about efficient and scalable probabilistic methods applied in large-scale settings of several domains such as Bayesian deep learning, deep generative models, hierarchical Bayesian models, and online/continual learning. I also have a broad interest in principled perspectives of deep learning including generalization, representation, uncertainty estimation, robustness, and so on.

News

• [Mar 2022] Our paper “Adaptive Infinite Dropout for Noisy and Sparse Data Streams” is accepted to Machine Learning journal.

• [Oct 2021] Our paper “Structured Dropout Variational Inference for Bayesian Neural Networks” is accepted to NeurIPS 2021.

• [Jan 2021] Our paper “Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein” is accepted to ICLR 2021.