tf-yarn is a Python library we have built at Criteo for training TensorFlow models on a YARN cluster. It supports running on one worker or on multiple workers with different distribution strategies, it can run on CPUs or GPUs and...

Professor Noureddine El Karoui (center) with colleagues at Criteo After working on theoretical questions in high-dimensional statistics as an academic at UC, Berkeley, I felt I wanted to see what statistics and machine learning were at industrial scale....

It’s been a year since we launched our AI Lab to drive and shape innovation within the AI field. Among all, we pay attention to give back to the community by sharing our works at top machine learning...

Five Criteos attended on March 27th & 28th the conference ScaledML 2019 at the Computer History Museum in Mountain View. It was the 4th edition of this conference focusing on Scaling ML models, data, algorithms, & infrastructure. The lineup of speakers was impressive:...

At Criteo AI Lab, we are using more and more complex machine learning (ML) models every day. This means that we have many more hyper-parameters to tune. A lot of ML model tuning used to be done by...

We were there for the 2019 edition of AAAI that took place in Honolulu, Hawaii and we wanted to share with you our thoughts and highlights. It’s in the air … Taking a step back on the ML...

Please accept YouTube cookies to play this video. By accepting you will be accessing content from YouTube, a service provided by an external third party. YouTube privacy policy If you accept this notice, your choice will be saved...

Introduction  Every two years, the French Society of Statistiques (SFdS) organizes a conference on a statistical topic for a week.   This year was devoted to Causality, starting from philosophical introduction to practical sessions on Bayesian networks.  As a researcher in...

Context As hype is mounting around deep learning, do we still need to care about plain nearest neighbors search? There is a recurring pattern in the deep learning pipelines: learn a representation for objects, and perform “simple” operations...

International Conference on Learning Representations (ICLR) is one of the leading conferences in machine learning out there, attracting thousands of participants from academia and industry each year. One of the great things about this conference is its reviewing...