Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
projects
Oríon: A framework for distributed hyperparameter optimisation
I am the lead developer of Oríon, an open-source framework developed at Mila for distributed black-box optimization. Its purpose is to serve as a meta-optimizer for machine learning models and training, as well as a flexible experimentation platform for large-scale asynchronous optimization procedures.
Mahler: Orchestration engine for high latency systems and dynamic workflows
For my research projects I developed a framework to automatically set up all available clusters and deploy my experiments. With Mahler, I can wrap the super computer schedulers to gain more control over my workflow, better resiliency, and better automation.
Track: Generic logger backend for machine learning
Track is a generic logger backend developed at Mila that can serve as a bridge between different logging libraries for machine learning. The goal is to provide a backend for Oríon so that users can use their own logger without any modification and simply configure Oríon to use the proper bridge with Track.
Kleiṓ: Experiment management for machine learning
Kleiṓ is an experiment manager, a logging journal of all data describing your experiments. Its purpose is to provide an automatic tool to log extensive environment information, including a script’s code version, system specification, and script configuration.
publications
Combining modality specific deep neural networks for emotion recognition in video
Samira Ebrahimi Kahou, Christopher Pal, Xavier Bouthillier, Pierre Froumenty, Çaglar Gülçehre, Roland Memisevic, Pascal Vincent, Aaron Courville, Yoshua Bengio, Raul Chandias Ferrari and others
Proceedings of the 15th ACM on International conference on multimodal interaction, 2013
Add except…
Dropout as data augmentation
Xavier Bouthillier, Kishore Konda, Pascal Vincent and Roland Memisevic
arXiv preprint arXiv:1506.08700, 2015
Add except…
Efficient exact gradient update for training deep networks with very large sparse targets
Pascal Vincent, Alexandre De Brébisson and Xavier Bouthillier
Advances in Neural Information Processing Systems, 2015
Add except…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov and others
arXiv preprint arXiv:1605.02688, 2016
Add except…
Emonets: Multimodal deep learning approaches for emotion recognition in video
Samira Ebrahimi Kahou, Xavier Bouthillier, Pascal Lamblin, Caglar Gulcehre, Vincent Michalski, Kishore Konda, Sébastien Jean, Pierre Froumenty, Yann Dauphin, Nicolas Boulanger-Lewandowski and others
Journal on Multimodal User Interfaces, 2016
Add except…
Exact gradient updates in time independent of output size for the spherical loss family
Pascal Vincent, Alexandre de Brébisson and Xavier Bouthillier
arXiv preprint arXiv:1606.08061, 2016
Add except…
An evaluation of fisher approximations beyond kronecker factorization
César Laurent, Thomas George, Xavier Bouthillier, Nicolas Ballas and Pascal Vincent
Workshop at International Conference on Learning Representations, 2018
Add except…
Oríon: Experiment Version Control for Efficient Hyperparameter Optimization
Christos Tsirigotis, Xavier Bouthillier, François Corneau-Tremblay, Peter Henderson, Reyhane Askari, Samuel Lavoie-Marchildon, Tristan Deleu, Dendi Suhubdy, Michael Noukhovitch, Frédéric Bastien and others
AutoML Workshop at the International Conference on Machine Learning, 2018
Add except…
Fast approximate natural gradient descent in a kronecker factored eigenbasis
Thomas George, César Laurent, Xavier Bouthillier, Nicolas Ballas and Pascal Vincent
Advances in Neural Information Processing Systems, 2018
Add except…
Unreproducible Research is Reproducible
Xavier Bouthillier, César Laurent and Pascal Vincent
International Conference on Machine Learning, 2019
Add except…
Improving Reproducibility of Benchmarks
Xavier Bouthillier
CiML Workshop at Advances in Neural Information Processing Systems, 2019
Add except…
Survey of machine-learning experimental methods at NeurIPS2019 and ICLR2020
Xavier Bouthillier, Gaël Varoquaux
Technical Report hal-02447823, 2020
Add except…
Accounting for Variance in Machine Learning Benchmarks
Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi, Assya Trofimov, Brennan Nichyporuk, Justin Szeto, Nazanin Mohammadi Sepahvand, Edward Raff, Kanika Madan, Vikram Voleti, Samira Ebrahimi Kahou, Vincent Michalski, Tal Arbel, Chris Pal, Gael Varoquaux, Pascal Vincent
Machine Learning and Systems (MLSys 2021), 2021
Add excerpt…
talks
Introduction au langage de programmation Python
Published:
Add except…
Oríon: Experiment Version Control for Efficient Hyperparameter Optimization
Published:
Add except…
Tutorial on Oríon
Published:
Add except…
Introduction à l’intelligence artificielle
Published:
Add except…
Intelligence artificielle: Une fabrique à outils
Published:
Add except…
Introduction à l’intelligence artificielle
Published:
Add except…
Unreproducible Research is Reproducible
Published:
Add except…
Reproducibility in AI
Published:
Add except…
Unreproducible Research is Reproducible
Published:
Add except…
Oríon: A framework for distributed hyperparameter optimisation
Published:
Add except…
Reproducibility in machine learning, or why benchmarks are lotteries
Published:
Add except…
Oríon: A framework for distributed hyperparameter optimisation
Published:
Add except…
Unreproducible Research is Reproducible
Published:
Add except…
Reproducibility & Hyperparameter Optimization with Oríon
Published:
Add except…
Orion Showcase @IBM
Published:
Add except…
Table ronde au CBPQ
Published:
Add except…
Orion Showcase @IBM
Published:
Add except…
On a quest for more trustworthy scientific conclusions in Machine Learning
Published:
Add except…
Oríon - A framework for distributed hyperparameter optimisation
Published:
Add except…
Practical Approaches for Efficient Hyperparameter Optimization
Published:
Add except…
Accounting for Variance in Machine Learning Benchmarks
Published:
Add except…
Black-Box Optimization using Dask with Oríon
Published:
Add except…
Oríon - Librarie pour l’optimisation de boîtes noires et hyperparamètres
Published:
Add except…
Oríon Showcase @IBM
Published:
Add except…
Practical approaches for efficient hyperparameter optimization with Oríon
Published:
Add except…
Accounting for Variance and HPO in Machine Learning Benchmarks
Published:
Add except…
Reliability of benchmarks and why HPO is important
Published:
Add except…
How do we get more people to use HPO
Published:
Add except…
Oríon Showcase @IBM
Published:
Add except…
Thesis Defense: Accounting for Variance and HPO in Machine Learning Benchmarks
Published:
Add except…
Le petit scientifique numérique
Published:
Add except…
Did We Forget about the Canonical Source of Variance in Machine Learning Pipelines?
Published:
Add except…
Accounting for Variance in Machine Learning Benchmarks
Published:
Add except…
Accounting for Variance and HPO in Machine Learning Benchmarks
Published:
Add except…
Accounting for Variance and HPO in Machine Learning Benchmarks
Published:
Add except…
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.