Leon Bottou

Research Lead

I received the Diplôme d’Ingénieur de l’École Polytechnique (X84) in 1987, the Magistère de Mathématiques Fondamentales et Appliquées et d’Informatique from École Normale Superieure in 1988, and a PhD in computer science from Université de Paris-Sud in 1991. I went to AT&T Bell Laboratories, AT&T Labs, NEC Labs America and Microsoft Research. I joined the Facebook AI Research in March 2015.

The long term goal of my research is to understand how to build human-level intelligence. Although reaching this goal requires conceptual advances that cannot be anticipated at this point, it certainly entails clarifying how to learn and how to reason. My best known contributions are my work on “deep” neural networks in the 1990s, large scale learning in the 2000s, and possibly my more recent work on causal inference in learning systems. I am also known for the DjVu document compression technology.


AI, machine learning, optimization, computer vision, signal processing, natural language processing and data compression

Latest Publications

Cold Case: the Lost MNIST Digits

Chhavi Yadav, Leon Bottou

NeurIPS - December 9, 2019

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

Aaron Defazio, Leon Bottou

NeurIPS - December 8, 2019

First-order Adversarial Vulnerability of Neural Networks and Input Dimension

Carl-Johann Simon-Gabriel, Yann Ollivier, Bernhard Scholkopf, Leon Bottou, David Lopez-Paz

ICML - June 9, 2019

SING: Symbol-to-Instrument Neural Generator

Alexandre Défossez, Neil Zeghidour, Nicolas Usunier, Leon Bottou, Francis Bach

NIPS 2018 - October 26, 2018

Optimization Methods for Large-Scale Machine Learning

Leon Bottou, Frank E. Curtis, Jorge Nocedal

SIAM Review - May 8, 2018

Empirical Analysis of the Hessian of Over-Parametrized Neural Networks

Levent Sagun, Utku Evci, V. Ugur Güney, Yann Dauphin, Leon Bottou

ICLR 2018 - April 30, 2018

Geometrical Insights for Implicit Generative Modeling

Leon Bottou, Martin Arjovsky, David Lopez-Paz, Maxime Oquab

arXiv - March 12, 2018

Wasserstein Generative Adversarial Networks

Martin Arjovsky, Soumith Chintala, Leon Bottou

ICML 2017 - August 6, 2017

Discovering Causal Signals in Images

David Lopez-Paz, Robert Nishihara, Soumith Chintala, Bernhard Scholkopf, Leon Bottou

CVPR 2017 - July 21, 2017

Towards Principled Methods for Training Generative Adversarial Networks

Martin Arjovsky, Leon Bottou

ICLR 2017 - April 24, 2017

No Regret Bound for Extreme Bandits

Robert Nishihara, David Lopez-Paz, Leon Bottou

ArXiv - August 12, 2015

Counterfactual Reasoning and Learning Systems: The Example of Computational Advertising

Leon Bottou, Jonas Peters, Joaquin Quiñonero Candela, Denis Charles, Max Chickering, Elon Portugaly, Dipankar Ray, Patrice Simard, Ed Snelson

JMLR - December 16, 2013