I am a final year Ph.D. student in the Sierra Team, which is part of the DI/ENS (Computer Science Department of École Normale Supérieure). I have graduated from Moscow Institute of Physics and Technology in 2015 and got a Master Degree in Applied Mathematics and Informatics. I am currently supervised by Francis Bach. My research interests are graphical models, approximate learning & inference, convex optimization and statistics.

Publications

Marginal Weighted Maximum Log-likelihood for Efficient Learning of Perturb-and-Map models
Tatiana Shpakova, Francis Bach and Anton Osokin
In Proceedings of the Uncertainty in Artificial Intelligence (UAI) 2018.
Parameter Learning for Log-supermodular Distributions
Tatiana Shpakova and Francis Bach
In Advances in Neural Information Processing Systems (NIPS) 2016.

Talks & Workshops

August 2018, Parameter Learning for Log-supermodular Distributions and Beoynd, Yandex seminar, Moscow.
June 2017, Parameter Learning for Log-supermodular Distributions, SPARS Workshop, Lisbon.
December 2016, Parameter Learning for Log-supermodular Distributions, Women in Machine Learning Workshop, Barcelona.
December 2016, Parameter Learning for Log-supermodular Distributions, Second Christmas Colloquium on Computer Vision, Skoltech, Moscow.

Additional Info

My CV
My LinkedIn
My Google Scholar