Timezone: »

Machine Learning for Combinatorial Optimization + Q&A
Maxime Gasse · Simon Bowly · Chris Cameron · Quentin Cappart · Jonas Charfreitag · Laurent Charlin · Shipra Agrawal · Didier Chetelat · Justin Dumouchelle · Ambros Gleixner · Aleksandr Kazachkov · Elias Khalil · Pawel Lichocki · Andrea Lodi · Miles Lubin · Christopher Morris · Dimitri Papageorgiou · Augustin Parjadis · Sebastian Pokutta · Antoine Prouvost · Yuandong Tian · Lara Scavuzzo · Giulia Zarpellon

Thu Dec 09 10:45 AM -- 11:05 AM (PST) @
Event URL: https://www.ecole.ai/2021/ml4co-competition/ »

The Machine Learning for Combinatorial Optimization (ML4CO) competition aims at improving a state-of-the-art mathematical solver by replacing key heuristic components with machine learning models trained on historical data. To that end participants will compete on the three following challenges, each corresponding to a distinct control task arising in a branch-and-bound solver: producing good solutions (primal task), proving optimality via branching (dual task), and choosing the best solver parameters (configuration task). Each task is exposed through an OpenAI-gym Python API build on top of the open-source solver SCIP, using the Ecole library. Participants can compete in any subset of the proposed challenges. While we encourage solutions derived from the reinforcement learning paradigm, any algorithmic solution respecting the competition's API is accepted.

Author Information

Maxime Gasse (Polytechnique Montréal)

I am a machine learning researcher within the Data Science for Real-Time Decision Making Canada Excellence Research Chair (CERC), and also part of the MILA research institute on artificial intelligence in Montréal, Canada. The question that motivates my research is: can machines think? My broad research interests include: - probabilistic graphical models and their theoretical properties (my PhD Thesis) - structured prediction, in particular multi-label classification - combinatorial optimization using machine learning (see our Ecole library) - causality, specifically in the context of reinforcement learning

Simon Bowly (Monash University)
Chris Cameron (University of British Columbia)
Quentin Cappart (Polytechnique Montréal)
Jonas Charfreitag (Uni Bonn)
Laurent Charlin (MILA / U.Montreal)
Shipra Agrawal (Columbia University)
Didier Chetelat (Polytechnique Montreal)
Justin Dumouchelle (Polytechnique Montréal)
Ambros Gleixner (Zuse Institute Berlin and HTW Berlin)
Aleksandr Kazachkov (University of Florida)
Elias Khalil (University of Toronto)
Pawel Lichocki (Google Research)
Andrea Lodi (École Polytechnique Montréal)
Miles Lubin (Google Research)
Christopher Morris (Mila, McGill University)
Dimitri Papageorgiou (ExxonMobil Corporate Research)
Augustin Parjadis (Polytechnique Montréal)
Sebastian Pokutta (Zuse Institute Berlin)
Antoine Prouvost (Mila)
Yuandong Tian (Facebook AI Research)
Lara Scavuzzo (TU Delft)
Giulia Zarpellon (Polytechnique Montreal)

More from the Same Authors