Philippe Brouillard

Philippe Brouillard

PhD Student

Université de Montréal

MILA

Biography

I am Philippe Brouillard, a PhD student cosupervised by Dhanya Sridhar and Alexandre Drouin at the Université de Montréal (UdeM) and at Mila, the Quebec Artificial Intelligence Institute. I am presently doing an internship at ServiceNow Research.

My research interests include causal discovery, causal representation learning, machine learning, and how to combine them!

Download my résumé (will be added soon).

Interests
  • Causal discovery
  • Causal representation learning
  • Machine learning
Education

  • PhD in Computer Science

    UdeM

  • MSc in Computer Science, 2021

    UdeM

  • BSc in Mathematics, 2017

    UdeM

  • BSc in Psychology, 2014

    UQAM

Publications

Philippe Brouillard, Perouz Taslakian, Alexandre Lacoste, Sébastien Lachapelle, Alexandre Drouin (2022). Typing Assumptions Improve Identification in Causal Discovery. In CLeaR 2022.

PDF Cite

Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Simon Lacoste-Julien, Alexandre Drouin (2020). Differentiable Causal Discovery with Interventional Data. In NeurIPS 2020.

PDF Cite

Philippe Brouillard, Sébastien Lachapelle, Alexandre Lacoste, Alexandre Drouin (2020). Gradient-based Neural DAG Learning with Intervention. In Causal Learning for Decision Making workshop, ICLR 2020.

PDF Cite

Sébastien Lachapelle, Philippe Brouillard, Tristan Deleu, Simon Lacoste-Julien (2020). Gradient-Based Neural DAG Learning. In ICLR 2020.

PDF Cite

Talks

Typing Assumptions Improve Identification in Causal Discovery
Causal discovery from observational data is a challenging task to which an exact solution cannot always be identified. Under …
Apr 11, 2022 4:00 AM — 4:00 AM Oral presentation at CLeaR 2022 (Eureka, CA)
Typing Assumptions Improve Identification in Causal Discovery (MAIS)
Causal discovery from observational data is a challenging task to which an exact solution cannot always be identified. Under …
Oct 31, 2021 4:00 AM — 4:00 AM Montreal AI Symposium (MAIS) 2021
Typing Assumptions Improve Identification in Causal Discovery (ICML Workshop)
Causal discovery from observational data is a challenging task to which an exact solution cannot always be identified. Under …
Jul 23, 2021 4:00 AM — 4:00 AM Oral Presentation at The Neglected Assumptions in Causal Inference Workshop, ICML 2021
Differentiable Causal Discovery with observational and interventional data
Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the …
May 19, 2021 4:00 AM — 4:00 AM Invited Talk at Element AI
Differentiable Causal Discovery with Interventional Data
Learning a causal directed acyclic graph from data is a challenging task that involves solving a combinatorial problem for which the …
Nov 26, 2020 5:00 AM — 5:00 AM Spotlight at NeurIPS 2020 (Virtual)
See all events

Contact