Sixin Zhang


I am currently Maitre de Conference at INP-Toulouse and IRIT (site ENSEEIHT), Toulouse, France. My website is Here.

I was a PhD student (2010-2016) at Courant Institute of Mathematical Sciences, NYU. My advisor is Yann LeCun. I obtained my Master degree in Mathematics and Machine Learning at Paris VI and ENS Cachan (2008-2010). My undergraduate education was in Mathematics and Information Science at Shanghai University (2004-2008). In the summer of 2012, I interned at Google in studying large-scale distributed learning with Samy Bengio and the Google Brain Team. I also had an internship in 2010 at Credit Agricole Cheuvreux, studying with Charles-Albert Lehalle and Romain Burgot on the news impact on stock market. My PhD thesis is available Here.

Research interests

Optimization, Machine Learning, Statistics and Dynamical Systems.


NIPS 2011 Optimization Challenge.

Master dissertation News Impact on Stock Market.

Research study guided by Lucien Birgé on the classical Maximum likelihood estimator.


Tom Schaul, Sixin Zhang, Yann LeCun. No more pesky learning rates. ICML 28 (3) : 343–351, 2013.

Li Wan, Matthew Zeiler, Sixin Zhang, Yann LeCun, Rob Fergus. Regularization of Neural Networks using DropConnect, ICML 28 (3) : 1058–1066, 2013.

Sixin Zhang, Anna Choromanska, Yann LeCun. Deep learning with Elastic Averaging SGD. NIPS 2015. The source code of the EASGD/EAMSGD algorithm is available on github.

Personal interests

recollecting some memory

Mail Address

INP ENSEEIHT 2, rue Camichel, BP 7122, 31071 Toulouse Cedex 7