Deep Learning and Combinatorial Optimization

February 22 - 25, 2021

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, February 22, 2021

SESSION CHAIR: Louis-Martin Rousseau (École Polytechnique de Montréal)

Morning Session

7:55 - 8:00 Welcome & Opening Remarks (Dima Shlyakhtenko)
8:00 - 8:25
8:35 - 9:00
Ron Kimmel (Technion - Israel Institute of Technology)

Learning Geometry
PDF Presentation

 
9:10 - 9:25 Break
9:25 - 9:50
10:00 - 10:25
Xavier Bresson (Nanyang Technological University, Singapore)

The Transformer Network for the Traveling Salesman Problem
PDF Presentation

 
10:35 - 10:50 Break
10:50 - 11:15
11:25 - 11:50

Tuesday, February 23, 2021

SESSION CHAIR: Wouter Kool (University of Amsterdam)

Morning Session

8:00 - 8:25
Sebastian Pokutta (Konrad-Zuse-Zentrum für Informationstechnik (ZIB))

Structured ML Training via Conditional Gradients
PDF Presentation

 
8:35 - 9:00
9:10 - 9:25 Break
9:25 - 9:50
10:00 - 10:25
10:35 - 10:50 Break
10:50 - 11:15
11:25 - 11:50
 
12:00 - 12:25
Petar Veličković (DeepMind Technologies)

Reasoning on Natural Inputs
PDF Presentation

 

Wednesday, February 24, 2021

SESSION CHAIR: Kyle Cranmer (New York University)

Morning Session

8:00 - 8:25
 
8:35 - 9:00
9:10 - 9:25 Break
9:25 - 9:50
10:00 - 10:25
Santanu Dey (Georgia Institute of Technology)

Solving SDPs by using sparse PCA
PDF Presentation

 
10:35 - 10:50 Break
10:50 - 11:15
11:25 - 11:50
12:00 - 12:25
 

Thursday, February 25, 2021

SESSION CHAIR: Petar Veličković (DeepMind Technologies)

Morning Session

8:00 - 8:25
Zico Kolter (Carnegie Mellon University)

Fast semidefinite programming for (differentiable) combinatorial optimization

 
8:35 - 9:00
Stefano Gualandi (Università di Pavia)

Discrete Optimal Transport by Parallel Network Simplex

 
9:10 - 9:25 Break
9:25 - 9:50
Bistra Dilkina (University of Southern California (USC))

Decision-focused learning: integrating downstream combinatorics in ML
PDF Presentation

 
10:00 - 10:25
Stefanie Jegelka (Massachusetts Institute of Technology)

Task structure and generalization in graph neural networks
PDF Presentation

 
10:35 - 10:50 Break
10:50 - 11:15
11:25 - 11:50
12:00 - 12:25