Seminar Series: Supervised Quantile Normalization for Matrix Factorization using Optimal Transport

locationYouTube VinAI Research


locationProf. Marco Cuturi - Research Scientist, Google Brain, Paris

For this October episode, we’ll give you a view into Optimal Transport. Our special guest speaker, Prof. Marco Cuturi will present a talk on “Supervised Quantile Normalization for Matrix Factorization using Optimal Transport”. Marco Cuturi joined Google Brain, in Paris, in October 2018. He graduated from ENSAE (2001), ENS Cachan (Master MVA, 2002) and holds a PhD in applied maths obtained in 2005 at Ecole des Mines de Paris. He worked as a post-doctoral researcher at the Institute of Statistical Mathematics, Tokyo, between 11/2005 and 03/2007. He worked in the financial industry between 04/2007 and 09/2008. After working at the ORFE department of Princeton University between 02/2009 and 08/2010 as a lecturer, he was at the Graduate School of Informatics of Kyoto University between 09/2010 and 09/2016 as a tenured associate professor. He then joined ENSAE, the french national school for statistics and economics, in 9/2016, where he still teaches. His recent proposal to solve optimal transport using an entropic regularization has re-ignited interest in optimal transport and Wasserstein distances in the machine learning community. His work has recently focused on applying that loss function to problems involving probability distributions, e.g. topic models / dictionary learning for text and images, parametric inference for generative models, regression with a Wasserstein loss and probabilistic embeddings for words.

Abstract: “We present in this recent work ( a recent application of our framework to carry out “soft” sorting and ranking using regularized optimal transport. We expand this framework to include “soft” quantile normalization operators that can be differentiated efficiently, and apply it to the problem of dimensionality reduction: we ask how features can be normalized with a target distribution of quantiles to recover “easy to factorize” matrices. We provide algorithms to do this, as well as empirical evidence of recovery, and useful applications to genomics”.

Time: 2.30 pm – 3.30 pm (Vietnam time, GMT+7), Friday, Oct 16 2020

This is an online seminar and will be streaming on our YouTube VinAI Research.

You can rewatch the talk here:

Like us on Facebook: VinAI Research


Follow us on LinkedIn:

Send your CV now to or contact us via hotline: 0963936742 or 0838092942.

#VinAIResearch #SeminarSeries #VRSS

Upcoming Events