Leon Bottou

RESEARCH SCIENTIST | NEW YORK CITY, UNITED STATES

Léon received the Diplôme d’Ingénieur de l’École Polytechnique (X84), the Magistère de Mathématiques Fondamentales et Appliquées et d’Informatique from École Normale Supérieure, and a Ph.D. in Computer Science from Université de Paris-Sud. His research career has taken him to AT&T Bell Laboratories, AT&T Labs Research, NEC Labs America, and Microsoft. Léon then joined Facebook AI Research. The long-term goal of Léon's research is to understand and replicate human-level intelligence. Because this goal requires conceptual advances that cannot be anticipated, Léon’s research has followed many practical and theoretical turns including neural networks applications, stochastic gradient learning algorithms, statistical properties of learning systems, computer vision applications with structured outputs, and theory of large-scale learning. Léon's research aims to clarify the relation between learning and reasoning, with focus on the many aspects of causation (inference, invariance, reasoning, affordance, and intuition).

Leon's Publications

November 30, 2022

THEORY

A Simple Convergence Proof of Adam and Adagrad

Alexandre Defossez, Leon Bottou, Nicolas Usunier, Francis Bach

November 30, 2022

June 30, 2022

Rich Feature Construction for the Optimization-Generalization Dilemma

Leon Bottou, David Lopez-Paz, Jianyu Zhang

June 30, 2022

May 13, 2022

A Scaling Calculus for the Design and Initialization of ReLU Networks

Aaron Defazio, Leon Bottou

May 13, 2022

October 08, 2021

CORE MACHINE LEARNING

Linear unit-tests for invariance discovery

Benjamin Charles Aubin, Aga Slowik, Leon Bottou, David Lopez-Paz

October 08, 2021

November 21, 2019

RESEARCH

COMPUTER VISION

Cold Case: the Lost MNIST Digits

Leon Bottou, Chavvi Yadav

November 21, 2019

November 18, 2019

RESEARCH

SPEECH & AUDIO

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

Aaron Defazio, Leon Bottou

November 18, 2019

October 26, 2018

RESEARCH

SPEECH & AUDIO

SING: Symbol-to-Instrument Neural Generator

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

October 26, 2018