I am a PhD student at the IMAGINE lab, École des ponts ParisTech, supervised by Nikos Komodakis and Guillaume Obozinski. I got my MS in computer science at Oregon State University in March 2015. Before that, I took the MS courses in computer vision and artificial intelligence at Universitat Autònoma de Barcelona from 2011 to 2012. In a time long gone, I obtained my BE at Hangzhou Dianzi University in 2010.
I began my research on tree-structured models for object recognition. Structured prediction and graphical models caught my attention, which attract me to change my focus from computer vision to probabilistic machine learning. I spent some time to improve my math skills by taking courses such as real analysis, probability theory and optimization. My current research lies at the intersection of machine learning and computer vision, especially at the areas involving graphical models. For a large amount of time during my PhD, I develop new optimization algorithms for computationally intractable inference and learning problems in graphical models inspired by the advance of stochastic proximal optimization methods. I realize existing graphical models rely on heavy model assumptions which restrict their applications to certain real problems. Therefore, I am also attempting to articulate probabilistic models with deep neural networks, embracing challenges brought by the non-linearity and non-convexity.