Yuansi Chen

Yuansi Chen

Quick Bio:

I am a PhD candidate in the Department of Statistics at UC Berkeley. The research life in Berkeley started in the fall of 2013. I am advised by Prof. Bin Yu. During my PhD, I am fortunate to also work with Prof. Martin Wainwright and Prof. Jack Gallant.
My main research interests lie on statistical machine learning, optimization and the applications in neuroscience. In particular, I am interested in stability, sampling algorithms, convolutional neural networks and statistical problems that arise from computational neuroscience. Before my PhD study, I obtained my Diplome d'Ingénieur (Eng. Deg. in Applied Mathematics) at Ecole Polytechnique in France.

Curriculum Vitae (in pdf)

"The best thing about being a statistician, is that you get to play in everyone's backyard." -- John Tukey


The DeepTune framework for modeling and characterizing neurons in visual cortex area V4, [bioRxiv]
Reza Abbasi-Asl*, Yuansi Chen*, Adam Bloniarz, Michael Oliver, Ben Willmore, Jack Gallant, Bin Yu. Submitted to Proceedings of the National Academy of Sciences (PNAS)
Stability and Convergence Trade-off of Iterative Optimization Algorithms, [Arxiv]
Yuansi Chen, Chi Jin, Bin Yu. Submitted to Journal of Machine Learning Research (JMLR)
Log-concave sampling: Metropolis-Hastings algorithms are fast, [COLT][Arxiv][Code on Github]
Yuansi Chen*, Raaz Dwivedi*, Martin Wainwright, Bin Yu. Conference on Learning Theory (COLT) 2018
The longer journal version is submitted to Annals of Applied Probability (AoAP).
Fast MCMC Algorithms on Polytopes, [JMLR][Arxiv][C++ Implementation on Github]
Yuansi Chen*, Raaz Dwivedi*, Martin Wainwright, Bin Yu. Journal of Machine Learning Research (JMLR) 2018
Vaidya Walk: A Sampling Algorithm Based on Volumetric-Logarithmic Barrier, [IEEE]
Yuansi Chen*, Raaz Dwivedi*, Martin Wainwright, Bin Yu. Allerton Conference 2017
Fast and Robust Archetypal Analysis for Representation Learning, [CVPR][Arxiv][Code&Demo]
Yuansi Chen, Julien Mairal and Zaid Harchaoui. IEEE Computer Vision and Pattern Recognition (CVPR) 2014

* denotes equal contribution