Yuansi Chen

Yuansi Chen

Quick Bio:

I am currently a PhD candidate in Statistics department at Berkeley. The research life in Berkeley started in the fall of 2013.
My main research interests lie on statistical machine learning, optimization and neuroscience. In particular, I am interested in stability, sampling algorithms, convolutional neural networks and applications to computational neuroscience. I am advised by Professor Bin Yu. Before this, I did my bachelors (Diplome d'Ingenieur, in French) at Ecole Polytechnique in France.
My CV can be found here.

Github

Publications:

Stability and Convergence Trade-off of Iterative Optimization Algorithms, [Arxiv] Yuansi Chen, Chi Jin, Bin Yu. (to be submitted)
Log-concave sampling: Metropolis-Hastings algorithms are fast!, [Arxiv][Github] Yuansi Chen, Raaz Dwivedi, Martin Wainwright, Bin Yu. (to be submitted)
Fast MCMC Algorithms on Polytopes, [Arxiv] Yuansi Chen, Raaz Dwivedi, Martin Wainwright, Bin Yu. (to be submitted)
Vaidya Walk: A Sampling Algorithm Based on Volumetric-Logarithmic Barrier, [PDF] Yuansi Chen, Raaz Dwivedi, Martin Wainwright, Bin Yu. Allerton Conference 2017
Fast and Robust Archetypal Analysis for Representation Learning, [PDF][Arxiv][demo] Yuansi Chen, Julien Mairal and Zaid Harchaoui. IEEE Computer Vision and Pattern Recognition (CVPR) 2014