MINDS Winter School and Workshop 2021

/ December 8, 2020/ Uncategorized

2021 TRIPODS Winter School & Workshop on Graph Learning and Deep Learning

This event aims to bring together experts in machine learning, statistical inference and learning on graphs, and optimization to share basic principles, recent research results, and practical ideas, on the foundations of graph and deep learning.

A series of tutorials and hands-on sessions will be virtually presented over the first week, followed by a workshop covering recent results on the area,  with opportunities for discussion with peers and leaders in the field.

TRIPODS Winter School will be held January 6-8th, 2021, with workshops held January 13-15. Please register here

Confirmed Speakers

Edo Airoldi Associate Professor Harvard University	Taco Cohen Researcher Qualcomm	William Hamilton Assistant Professor McGill University	Stefanie Jegelka Associate Professor MIT	George Karypis Senior Principal Scientist Amazon Web Services
Eric Kolaczyk Professor Boston University	Gitta Kutyniok Professor LMU Munich	Elizaveta Levina Professor University of Michigan	Jason Lee Assistant Professor Princeton University	Jure Leskovec Associate Professor Stanford University
Guido Montúfar Assistant Professor UCLA	Hanie Sedghi Research Scientist Google Brain	Alex Smola Director Amazon Web Services	Matus Telgarsky Assistant Professor UIUC

Agenda

Times shown in EST

Time	Session	Speaker	Presentation
Wednesday January 6
11:45AM		Rene Vidal	Welcome & Introduction
12:00PM	Tutorial	Matus Telgarsky	Generalization in Deep Learning
1:00PM	Tutorial	Jason Lee	Optimization Beyond Linearization in Neural Networks
2:00PM	Break
2:30PM	Tutorial	Eric Kolaczyk	Statistical Analysis on Network Data
3:30PM	Tutorial	William Hamilton	Representation Learning on Graphs
4:30PM		Alex Smola	Practicum Warmup
Thursday January 7
12:00PM-5:00PM	Practicum	Alex Smola	DNNs Practicum
Friday January 8
12:00PM	Tutorial	Stefanie Jegelka	Graph Neural Networks
1:00PM	Tutorial	Gitta Kutyniok	The Expressive Power of Deep Learning
2:00PM	Break
2:30PM	Tutorial	Edo Airoldi	Applications of Graph Learning
3:30PM	Tutorial	Taco Cohen	Equivariant Networks
Wednesday January 13
12:00PM	Workshop	Matus Telgarsky	Improved analyses and rates of gradient descent’s implicit bias
12:45PM	Workshop	Jure Leskovec	Reasoning Over Knowledge Graphs using Embeddings
1:30PM	Workshop	Jason Lee	Provable representation learning in deep learning
2:15PM	Break
2:45PM	Workshop	Stefanie Jegelka	Learning and Generalization in Graph Neural Networks
3:30PM	Workshop	Hanie Sedghi	What is being transferred in transfer learning?
4:15PM	Workshop	Eric Kolaczyk	Why Aren’t Network Summary Statistics Accompanied by Uncertainty Statements?
Thursday January 14
12:00PM-5:00PM	Practicum	George Karypis	Graph NNs Practicum
Friday January 15
12:00PM	Workshop	Edo Airoldi	Leveraging probabilistic models for designing causal analyses resilient to model failure
12:45PM	Break
1:30PM	Workshop	Guido Montufar	Implicit bias of gradient descent for mean squared error regression with wide neural networks
2:15PM	Break
2:45PM	Workshop	Elizaveta Levina	Hierarchical community detection by recursive partitioning
3:30PM	Workshop	William Hamilton	Learning Dynamic Belief Graphs to Generalize on Text-Based Games
4:15PM	Panel	George Karypis, Eric Kolaczyk & Elizaveta Levina	Future Directions in Graph Learning & Deep Learning