Xavier Bouthillier

PhD student, MILA, Université de Montréal

Joined

February 2018

Names

Xavier Bouthillier

Emails

****@umontreal.ca (Confirmed)

****@iro.umontreal.ca

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

MILA, Université de Montréal (umontreal.ca)

2014 – Present

PhD student

Mila, Université de Montréal (umontreal.ca)

2014 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Pascal Vincent

2014 – Present

Coauthor

Samira Ebrahimi Kahou

2013 – 2013

Coauthor

Christopher J Pal

2013 – 2013

Coauthor

Pierre Froumenty

2013 – 2013

Coauthor

Caglar Gulcehre

2013 – 2013

Coauthor

Roland Memisevic

2013 – 2013

Coauthor

Aaron Courville

2013 – 2013

Coauthor

Yoshua Bengio

2013 – 2013

Expertise

No areas of expertise listed

Publications

LMEMs for post-hoc analysis of HPO Benchmarking
Anton Merlin Geburek, Neeratyoy Mallik, Danny Stoll, Xavier Bouthillier, Frank Hutter
- AutoML 2024 Workshop
- Readers: Everyone
Improving Reproducibility of Benchmarks
Xavier Bouthillier
- 13 Jun 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
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, Dmitriy Serdyuk, Tal Arbel, Christopher Pal, Gael Varoquaux, Pascal Vincent
- 13 Jun 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
Unreproducible Research is Reproducible
Xavier Bouthillier, César Laurent, Pascal Vincent
- 2019 (modified: 11 Nov 2022)
- ICML 2019
- Readers: Everyone
Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis
Thomas George, César Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent
- 2018 (modified: 11 Nov 2022)
- NeurIPS 2018
- Readers: Everyone
Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
Pascal Vincent, Alexandre de Brébisson, Xavier Bouthillier
- 2015 (modified: 11 Nov 2022)
- NIPS 2015
- Readers: Everyone

Xavier Bouthillier

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

LMEMs for post-hoc analysis of HPO Benchmarking

Improving Reproducibility of Benchmarks

Accounting for Variance in Machine Learning Benchmarks

Unreproducible Research is Reproducible

Fast Approximate Natural Gradient Descent in a Kronecker Factored Eigenbasis

Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets

Co-Authors