Workshop IV: Deep Geometric Learning of Big Data and Applications - IPAM

Workshop IV: Deep Geometric Learning of Big Data and Applications

Part of the Long Program Geometry and Learning from Data in 3D and Beyond
May 20 - 24, 2019

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, May 20, 2019

Morning Session

08:00-08:55
Check-In/Light Breakfast (Hosted by IPAM)
08:55-09:00
Welcome & Opening Remarks: Dean Miguel García-Garibay (Dean of Physical Sciences, UCLA) and Dima Shlyakhtenko (Director, IPAM)
09:00-09:40
Arthur Szlam (Facebook)
Language, Interaction, and Perception in Minecraft
09:50-10:10
Break
10:10-10:50
Soumith Chintala (Facebook AI Research)
Automatic Differentiation, PyTorch and Graph Neural Networks
11:00-11:20
Break
11:20-12:00
Jeremias Sulam (Johns Hopkins University)
Deep Learning as Sparsity Enforcing Algorithms

Afternoon Session

12:10-14:00
Lunch (on your own)
14:00-14:40
Marc Pollefeys (ETH Zurich)
Semantic 3D reconstruction
14:50-15:10
Break
15:10-15:50
Bahram Jalali (University of California, Los Angeles (UCLA))
Low Latency Deep Imaging Cytometry
16:00-18:00
Poster Session & Reception (Hosted by IPAM)

Tuesday, May 21, 2019

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:40
Tom Goldstein (University of Maryland)
A theoretical look at adversarial examples: a perspective from high-dimensional geometry
09:50-10:10
Break
10:10-10:50
Hongyang Zhang (Carnegie Mellon University)
Theoretically Principled Trade-off between Robustness and Accuracy
11:00-11:20
Break
11:20-12:00
Roy Lederman (Yale University)
On Inverse Problems and Unsupervised Learning in the Mapping of Heterogeneous Molecular Structures in Cryo-Electron Microscopy

Afternoon Session

12:10-14:00
Lunch (on your own)
14:00-14:40
Xavier Bresson (National University of Singapore)
Graph Convolutional Neural Networks for Molecule Generation and Travelling Salesman Problem
14:50-15:10
Break
15:10-15:50
Hamed Pirsiavash (University of Maryland Baltimore County)
Self-supervised learning for visual recognition

Wednesday, May 22, 2019

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:40
Jian Tang (HEC Montréal)
GMNN: Graph Markov Neural Networks
09:50-10:10
Break
10:10-10:50
Thomas Kipf (Universiteit van Amsterdam)
Unsupervised Learning with Graph Neural Networks
11:00-11:20
Break
11:20-12:00
Jure Leskovec (Stanford University)
Deep Generative Models for Graphs: Methods & Applications

Afternoon Session

12:10-14:00
Lunch (on your own)
14:00-14:40
Mathias Niepert (NEC Laboratories Europe)
Relational Representation Learning with Graph Neural Networks
14:50-15:10
Break
15:10-15:50
Federico Monti (Universita della Svizzera Italiana)
Geometric Deep Learning: approaches and applications

Thursday, May 23, 2019

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:40
Mikhail Belkin (Ohio State University)
From classical statistics to modern machine learning
09:50-10:10
Break
10:10-10:50
Thiago Serra (Bucknell University)
Bounding and Counting Linear Regions of Deep Neural Networks
11:00-11:20
Break
11:20-12:00
Rene Vidal (Johns Hopkins University)
On the Implicit Bias of Dropout

Afternoon Session

12:10-14:00
Lunch (on your own)
14:00-14:40
Stanley Osher (University of California, Los Angeles (UCLA))
Unnormalized Optimal Transport
14:50-15:10
Break
15:10-15:50
Srikumar Ramalingam (University of Utah)
Deriving Equivalent Networks and hyperparameter optimization
16:00-16:20
Break
16:20-17:00
Luc Van Gool (ETH Zurich)
The creation of dense depth maps for autonomous cars
Printable Version