École des ponts ParisTech

6-8, Av Blaise Pascal

Champs-sur-Marne 77455

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.

- I am doing an internship at Amazon Cambridge supervised by Andreas Damianou and Pablo García Moreno.
- Our paper SDCA-Powered Inexact Dual Augmented Lagrangian Method for Fast CRF Learning accepted at AISTATS 2018.
- Gave a poster presentation at KAUST workshop on optimization and big data on fast CRF learning.
- Attended Data Science Summer School 2017 at Ecole polytechnique.
- I was at NIPS 2016 Barcelona.
- I am a volunteer of ICML 2015 at Lille.
- I am the mentor of a GSoC 2014 project for Shogun Machine Learning Toolbox: Structured Output Learning with Approximate Inference. See our IPython notebook by Jiaolong Xu.
- My GSoC 2013 project of general structured output models for Shogun Machine Learning Toolbox is finished. A IPython notebook is available.