Workshop III: Geometry of Big Data - IPAM

Workshop III: Geometry of Big Data

Part of the Long Program Geometry and Learning from Data in 3D and Beyond
April 29 - May 3, 2019

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, April 29, 2019

Morning Session

08:00-08:55
Check-In/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
Pradeep Ravikumar (Carnegie Mellon University)
DAGs with NO TEARS: Continuous Optimization for Structure Learning
09:50-10:05
Break
10:05-10:45
Ronen Talmon (Technion - Israel Institute of Technology)
Data Analysis with the Riemannian Geometry of Symmetric Positive-Definite Matrices
10:55-11:10
Break
11:10-11:50
Yusu Wang (Ohio State University)
Metric learning for persistence-based summaries and application to graph classification

Afternoon Session

12:00-13:30
Lunch (on your own)
13:30-14:10
Dejan Slepcev (Carnegie Mellon University)
Proper regularizers for semi-supervised learning
14:20-14:35
Break
14:35-15:15
Jianfeng Lu (Duke University Medical Center)
Solving for committor functions in high dimension
15:25-15:40
Break
15:40-16:20
Lorenzo Rosasco (Università di Genova)
A consistent framework for structure machine learning
16:30-18:00
Poster Session & Reception (Hosted by IPAM)

Tuesday, April 30, 2019

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:40
Frederic Chazal (Institut National de Recherche en Informatique et Automatique (INRIA))
On the density of expected persistence diagrams and its kernel based estimation
09:50-10:05
Break
10:05-10:45
Richard Samworth (University of Cambridge)
Log-concave density estimation: adaptation and high dimensions
10:55-11:10
Break
11:10-11:50
Nathan Srebro (TTI-Chicago)
Infinite-Width Bounded-Norm Networks: A View from Function Space

Afternoon Session

12:00-13:45
Lunch (on your own)
13:45-14:25
Andrea Montanari (Stanford University)
Some geometric surprises in modern machine learning
14:35-14:50
Break
14:50-15:30
Amit Singer (Princeton University)
Multi-target detection and cryo-EM imaging by autocorrelation analysis
15:40-15:55
Break
15:55-16:35
Rebecca Willett (University of Chicago)
Learning to Solve Inverse Problems in Imaging

Wednesday, May 1, 2019

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:40
Bin Dong (Peking University)
Bridging Deep Neural Networks and Differential Equations for Image Restoration and Beyond
09:50-10:05
Break
10:05-10:45
Marina Meila (University of Waterloo)
Manifold Learning for the Sciences
10:55-11:10
Break
11:10-11:50
Mahdi Soltanolkotabi (University of Southern California (USC))
Towards demystifying over-parameterization in deep learning

Afternoon Session

12:00-13:45
Lunch (on your own)
13:45-14:30
Stanley Osher (University of California, Los Angeles (UCLA))
PDE Approaches for Deep Learning
14:40-14:55
Break
14:55-15:35
Imre Risi Kondor (University of Chicago)
Covariant neural networks for learning physical systems
15:45-16:00
Break
16:00-16:40
Naftali Tishby (Hebrew University)
Topological transitions (and symmetries) of input representations in Deep Learning

Thursday, May 2, 2019

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:40
Richard Tsai (University of Texas at Austin)
Machine learning approaches for a few optimization problems involving lines-of-sight
09:50-10:05
Break
10:05-10:45
Bin Yu (University of California, Berkeley (UC Berkeley))
PCS workflow, interpretable machine learning, and DeepTune
10:55-11:10
Break
11:10-11:50
Hongkai Zhao (Duke University)
Intrinsic complexity: from approximation of random vectors and random fields to solutions of PDEs

Afternoon Session

12:00-13:45
Lunch (on your own)
13:45-14:25
Zuowei Shen (National University of Singapore)
Deep Approximation via Deep Learning
14:35-14:50
Break
14:50-15:30
Joel Tropp (California Institute of Technology)
SketchySVD
15:40-15:55
Break
15:55-16:35
Jianfeng Cai (Hong Kong University of Science and Technology)
Solving Systems of Phaseless Equations: Riemannian Optimization and Global Geometry
Printable Version