David Lopez-Paz

I am a research scientist at Facebook AI Research in Paris, France. Here is my email and public key.


Learning about an exponential amount of conditional distributions
Mohamed Ishmael Belghazi, Maxime Oquab Yann LeCun, David Lopez-Paz
arXiv, 2018
Interpolation consistency training for semi-supervised learning
Vikas Verma, Alex Lamb, Juho Kannala, Yoshua Bengio David Lopez-Paz
arXiv, 2018
Manifold mixup: Better representations by interpolating hidden states
Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, Aaron Courville, David Lopez-Paz, Yoshua Bengio
arXiv, 2018
Frequentist uncertainty estimates for deep learning
Natasa Tagasovska, David Lopez-Paz
NeurIPS Bayesian Deep Learning, 2018
SAM: Structural Agnostic Model, causal discovery and penalized adversarial learning
Diviyan Kalainathan, Olivier Goudet, Isabelle Guyon, David Lopez-Paz, Michèle Sebag
arXiv, 2018 (code)
Optimizing the latent space of generative networks
Piotr Bojanowski, Armand Joulin, David Lopez-Paz, Arthur Szlam
ICML, 2018
Adversarial vulnerability of neural networks increases with input dimension
Carl-Johann Simon-Gabriel, Yann Ollivier, Bernhard Schölkopf, Léon Bottou, David Lopez-Paz
arXiv, 2018
Geometrical insights for implicit generative modeling
Léon Bottou, Martín Arjovsky, David Lopez-Paz, Maxime Oquab
Springer's Braverman Readings in Machine Learning, 2018
mixup: Beyond empirical risk minimization
Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz
ICLR, 2018 (code)
Easing non-convex optimization with neural networks
David Lopez-Paz, Levent Sagun
ICLR Workshops, 2018 (code)
Causal discovery using proxy variables
Mateo Rojas-Carulla, Marco Baroni, David Lopez-Paz
ICLR Workshops, 2018
Learning Functional Causal Models with Generative Neural Networks
Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle Guyon, David Lopez-Paz, Michèle Sebag
Springer's Explainable and Interpretable Models in CV and ML, 2018 (code)
Gradient episodic memory for continuum learning
David Lopez-Paz, Marc'Aurelio Ranzato
NeurIPS, 2017 (code)
Patient-driven privacy control through generalized distillation
Berkay Celik, David Lopez-Paz, Patrick McDaniel
IEEE PAC, 2017
Revisiting classifier two-sample tests
David Lopez-Paz, Maxime Oquab
ICLR, 2017 (code)
Discovering causal signals in images
David Lopez-Paz, Robert Nishihara, Soumith Chintala, Bernhard Schölkopf, Léon Bottou
CVPR, 2017
From dependence to causation
David Lopez-Paz
Doctoral dissertation, 2016
Causal and statistical learning
Bernhard Schölkopf, Dominik Janzing, David Lopez-Paz
Oberwolfach Reports, 2016
Unifying distillation and privileged information
David Lopez-Paz, Léon Bottou, Bernhard Schölkopf, Vladimir Vapnik
ICLR, 2016 (code)
Minimax lower bounds for realizable transductive classification
Ilya Tolstikhin, David Lopez-Paz
arXiv, 2016
No regret bound for extreme bandits
Robert Nishihara, David Lopez-Paz, Léon Bottou
Non-linear causal inference using Gaussianity measures
Daniel Hernandez-Lobato, Pablo Morales Mombiela, David Lopez-Paz, Alberto Suarez
JMLR, 2016 (code)
The randomized causation coefficient
David Lopez-Paz, Krikamol Muandet, Benjamin Recht
JMLR, 2015 (code, talk)
Towards a learning theory of cause-effect inference
David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, Ilya Tolstikhin
ICML, 2015 (code)
Randomized nonlinear component analysis
David Lopez-Paz, Suvrit Sra, Alex Smola, Zoubin Ghahramani, Bernhard Schölkopf
ICML, 2014 (code, talk)
Two numerical models of Saturn rings temperature as measured by Cassini
Nicolas Altobelli, David Lopez-Paz et al.
Icarus, 2014
The randomized dependence coefficient
David Lopez-Paz, Philipp Hennig, Bernhard Schölkopf
NeurIPS, 2013 (code, talk)
Gaussian process vine copulas for multivariate dependence
David Lopez-Paz, José Miguel Hernández-Lobato, Zoubin Ghahramani
ICML, 2013 (code, talk)
Semisupervised domain adaptation with nonparametric copulas
David Lopez-Paz, José Miguel Hernández-Lobato, Bernhard Schölkopf
NeurIPS, 2012 (code, talk)


Statistical causal learning
Bernhard Schölkopf, Ilya Tolstikhin, David Lopez-Paz
Lake Como School of Advanced Studies, 2017
David Lopez-Paz
Machine Learning Summer School, 2017
Randomized algorithms
David Lopez-Paz
Machine Learning Summer School, 2016
Kernel methods
Rohit Babbar, David Lopez-Paz, Krikamol Muandet
Machine Learning Summer School, 2015
Graphical models in computer vision
Peter Gehler, Andreas Geiger, David Lopez-Paz
University of Tübingen, 2014/15
Graphical models in computer vision
Peter Gehler, David Lopez-Paz
University of Tübingen, 2013/14
Random projections
David Lopez-Paz, David Duvenaud,
University of Cambridge, 2014


Causal learning
Martin Arjovsky, Christina Heinze-Deml, Anna Klimovskaia, Maxime Oquab, Léon Bottou, David Lopez-Paz
NeurIPS, 2018
The theory of generative adversarial networks
Sebastian Nowozin, David Lopez-Paz
DALI, 2017 (videos)
Workshop on adversarial training
David Lopez-Paz, Alec Radford, Léon Bottou
NeurIPS, 2016
Second machine learning in Cambridge meeting
David Lopez-Paz, Sebastian Nowozin, Zoubin Ghahramani
Microsoft Research Cambridge, 2015
First machine learning in Cambridge meeting
David Lopez-Paz, Sebastian Nowozin, Zoubin Ghahramani
Microsoft Research Cambridge, 2014
Workshop on randomized methods for machine learning
David Lopez-Paz, Quoc Le, Alex Smola
NeurIPS, 2013