I am a postdoctoral fellow in the department of Electrical Engineering and Computer Science (EECS) at UC Berkeley, hosted by Michael I. Jordan. I am also a member of the RISELab and the Berkeley Artificial Intelligence Research Group (BAIR). I obtained my Ph.D. from the Sierra Team, which is part of the DI/ENS (Computer Science Department of École Normale Supérieure). I was supervised by Francis Bach and Alexandre d'Aspremont . My research interests are at the interface between optimization and statistics.

Publications

Averaging Stochastic Gradient Descent on Riemannian Manifolds
Nilesh Tripuraneni, Nicolas Flammarion, Francis Bach, Michael I. Jordan.
arXiv preprint, 2018.
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
Niladri S. Chatterji, Nicolas Flammarion, Yi-An Ma, Peter L. Bartlett, Michael I. Jordan.
arXiv preprint, 2018.
Stochastic Composite Least-Squares Regression with convergence rate O(1/n)
Nicolas Flammarion, Francis Bach.
Proceedings of the International Conference on Learning Theory (COLT), 2017.
Optimal rates of Statistical Seriation
Nicolas Flammarion, Cheng Mao and Philippe Rigollet.
Bernoulli (to appear).
Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
Aymeric Dieuleveut, Nicolas Flammarion and Francis Bach.
Journal of Machine Learning Research, 18(101):1−51, 2017.
Robust Discriminative Clustering with Sparse Regularizers
Nicolas Flammarion, Balamurugan Palaniappan and Francis Bach.
Journal of Machine Learning Research, 18(80):1-50, 2017.
From Averaging to Acceleration, There is Only a Step-size
Nicolas Flammarion, Francis Bach.
Proceedings of the International Conference on Learning Theory (COLT), 2015.

Teaching

MM1, Université Paris Diderot, 2014-2017.
Convex optimization and Probabilités, ENSAE, 2013-2014.