Marc’Aurelio Ranzato

Research Scientist

I joined Facebook AI Research in Fall 2013. I previously worked at Google on the Brain team, and before that, I was a post-doctoral fellow in Machine Learning at the University of Toronto working with Geoffrey Hinton. I did my PhD in computer science at New York University in Yann LeCun’s group. I am originally from Padova in Italy, where I graduated in Electronics Engineering. I am interested in machine learning, computer vision and, more generally, artificial intelligence. I have worked on unsupervised learning algorithms using both probabilistic graphical models and energy-based models. I also used these algorithms to build hierarchical models, called deep networks. I applied these models to a variety of applications, such as visual object recognition, speech recognition and text document retrieval. I am currently working on non-linear dynamical systems to analyze data streams.


I am co-organizing the first Deep Learning Symposium at NIPS 2015. Also, I am chairing the demo session at NIPS 2015. I have been serving as Area Chair for several conferences, including ICML, NIPS, CVPR and ICCV.

Useful links

An introductory lecture on convolutional neural networks for vision applications.


Machine learning (deep learning, energy based models, probabilistic graphical models, structure prediction), vision (low-level image statistics, image recognition, feature learning, image denoising), speech (acoustic modeling) and text processing (language modeling, topic modeling)

Latest Publications

arXiv - July 3, 2020

On The Evaluation of Machine Translation Systems Trained With Back-Translation

Sergey Edunov, Myle Ott, Marc'Aurelio Ranzato, Michael Auli

ICLR - April 1, 2020

Residual Energy-Based Models for Text Generation

Yuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam, Marc'Aurelio Ranzato

EMNLP - October 31, 2019

The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English

Francisco (Paco) Guzman, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, Marc'Aurelio Ranzato

Workshop on Asian Translation at EMNLP - October 31, 2019

Facebook AI’s WAT19 Myanmar-English Translation Task Submission

Peng-Jen Chen, Jiajun Shen, Matt Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc'Aurelio Ranzato

ICCV - October 28, 2019

Task-Driven Modular Networks for Zero-Shot Compositional Learning

Senthil Purushwalkam, Maximilian Nickel, Abhinav Gupta, Marc'Aurelio Ranzato

ICML - June 10, 2019

Mixture Models for Diverse Machine Translation: Tricks of the Trade

Tianxiao Shen, Myle Ott, Michael Auli, Marc'Aurelio Ranzato

ICLR - May 6, 2019

Efficient Lifelong Learning with A-GEM

Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny

ICLR - May 6, 2019

Multiple-Attribute Text Rewriting

Guillaume Lample, Sandeep Subramanian, Eric Michael Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, Y-Lan Boureau

EMNLP 2018 - October 31, 2018

Phrase-Based & Neural Unsupervised Machine Translation

Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato

ICML 2018 - July 13, 2018

Analyzing Uncertainty in Neural Machine Translation

Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato

NAACL 2018 - June 1, 2018

Classical Structured Prediction Losses for Sequence to Sequence Learning

Sergey Edunov, Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato

ICLR 2018 - April 30, 2018

Unsupervised Machine Translation Using Monolingual Corpora Only

Guillaume Lample, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato

ICLR 2018 - April 30, 2018

Word Translation Without Parallel Data

Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou

NIPS 2017 - December 4, 2017

Fader Networks: Manipulating Images by Sliding Attributes

Guillaume Lample, Neil Zeghidour, Nicolas Usunier, Antoine Bordes, Ludovic Denoyer, Marc'Aurelio Ranzato

NIPS 2017 - December 4, 2017

Gradient Episodic Memory for Continual Learning

David Lopez-Paz, Marc'Aurelio Ranzato

ICLR 2017 - April 24, 2017

Dialogue Learning with Human-in-the-Loop

Jiwei Li, Alexander Miller, Sumit Chopra, Marc'Aurelio Ranzato, Jason Weston

ICLR 2017 - April 24, 2017

Learning through Dialogue Interactions by Asking Questions

Jiwei Li, Alexander Miller, Sumit Chopra, Marc'Aurelio Ranzato, Jason Weston

ICLR - November 20, 2015

Sequence Level Training with Recurrent Neural Networks

Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, Wojciech Zaremba

ArXiv - June 25, 2015

Scale-Invariant Learning and Convolutional Networks

Mark Tygert, Arthur Szlam, Soumith Chintala, Marc'Aurelio Ranzato, Yuandong Tian, Wojciech Zaremba

ICLR - June 22, 2015

Learning Longer Memory in Recurrent Neural Networks

Tomas Mikolov, Armand Joulin, Sumit Chopra, Michael Mathieu, Marc'Aurelio Ranzato

CVPR 2015 - June 12, 2015

Web-Scale Training for Face Identification

Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf

ICLR workshop - December 19, 2014

Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews

Gregoire Mesnil, Tomas Mikolov, Marc'Aurelio Ranzato, Yoshua Bengio

ArXiv - December 19, 2014

Video (language) Modeling: a Baseline for Generative Models of Natural Videos

Marc'Aurelio Ranzato, Arthur Szlam, Joan Bruna, Michael Mathieu, Ronan Collobert, Sumit Chopra

CVPR - June 24, 2014

PANDA: Pose Aligned Networks for Deep Attribute Modeling

Ning Zhang, Manohar Paluri, Marc'Aurelio Ranzato, Trevor Darrell, Lubomir Bourdev

CVPR - June 24, 2014

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf

Latest News