Avatar

Yoan Russac

Machine Learning Researcher

Twitter

Biography

I am a Machine Learning Researcher within Twitter Cortex where I am part of the Recommender System team. I hold a PhD in Machine Learning from Ecole Normale Supérieure in the Center for Sciences of Data where I was lucky to be supervised by Olivier Cappé and Aurélien Garivier. My research interests include sequential learning with partial information feedback (more precisely bandits models) and more recently Deep Learning. The main objective of my PhD was to improve decision-making in uncertain and dynamic environments. In particular, I have worked on passively forgetting strategies that are well-suited for non-stationary environments and non-parametric algorithms.

Interests

  • Bandits
  • Machine Learning
  • Reinforcement Learning
  • Deep Learning

Education

  • PhD in Machine Learning, 2018-2022

    Ecole Normale Supérieure

  • MVA Master Degree, 2017-2018

    ENS-Paris Saclay

  • MSc in Statistics and Data Science, 2015-2018

    ENSAE- Institut Polytechnique de Paris

Experience

 
 
 
 
 

Machine Learning Researcher

Twitter

Mar 2022 – Present London, UK
 
 
 
 
 

Machine Learning Engineer Intern

Twitter

Jun 2021 – Aug 2021 London, UK
 
 
 
 
 

Applied Scientist Intern

Amazon

Jun 2018 – Nov 2018 Berlin, Germany
Research on non-stationarity and bandits.
 
 
 
 
 

Machine Learning Researcher Intern

Worldline

Jun 2017 – Sep 2017 Brussels, Belgium
Research on fraud detection using Word2Vec embeddings.

Recent & Upcoming Talks

Introduction to Linear Bandits

An introduction to Bandits and Linear Bandits

Non-Stationary Linear Bandits

In this talk a new deviation bound to control the weighted least-squares estimator in a Linear Bandit model is discussed.

Contact

  • 45 rue d'Ulm, Paris, 75005, France