Léon Bottou



  • Fellow
  • Learning in Machines & Brains


  • New York University
  • Facebook AI Research


  • France


PhD (Computer Science) Université de Paris-Sud
Diplôme d’Ingénieur de l’École Polytechnique
the Magistère de Mathématiques Fondamentales et Appliquées d’Informatique from École Normale Superieure


The long-term goal of Léon Bottou’s research is to understand how to replicate human-level intelligence.

Because this goal requires conceptual advances that cannot be anticipated, Leon’s research has followed many practical and theoretical turns: neural networks applications in the late 1980s, stochastic gradient learning algorithms and statistical properties of learning systems in the early 1990s, computer vision applications with structured outputs in the late 1990s, theory of large scale learning in the 2000s. During the last few years, Léon Bottou’s research aims to clarify the relation between learning and reasoning, with more and more focus on the many aspects of causation (inference, invariance, reasoning, affordance, and intuition.)


Blavatnik Award for Young Scientists, 2007

NeurIPS Test of Time Award: “The Tradeoffs of Large-Scale Learning", 2018

Relevant Publications

Wasserstein generative adversarial networks (2017)
M Arjovsky, S Chintala, L Bottou
International Conference on Machine Learning, 214-223

Counterfactual reasoning and learning systems (2013)
L Bottou, J Peters, J Quiñonero-Candela, DX Charles, DM Chickering, ...
The Journal of Machine Learning Research 14 (1), 3207-3260

The Tradeoffs of Large-Scale Learning (2007)
L Bottou, O Bousquet
Neural Information Processing Systems 20, 161-168

Fast kernel classifiers with online and active learning (2005)
A Bordes, S Ertekin, J Weston, L Bottou
Journal of Machine Learning Research 6 (Sep), 1579-1619

Gradient-based learning applied to document recognition (1998)
Y LeCun, L Bottou, Y Bengio, P Haffner
Proceedings of the IEEE 86 (11), 2278-2324