• Click on the titles of individual talks for abstract, slides and archived video.

All events take place in the Calvin Lab Auditorium.

–
Coffee and Check-In
–
Opening Remarks
–
Topic Modeling: A Provable Spectral Method
Ravi Kannan (Simons Institute, UC Berkeley)
–
Break
–
Exact Recovery via Convex Relaxations
Moses Charikar (Stanford University)
–
Break
–
The Impact of Regularization in Spectral Clustering
–
Lunch
–
Multiscale Analysis on and of Graphs
Mauro Maggioni (Duke University)
–
Break
–
Multiresolution Graph Models
Risi Kondor, University of Chicago
–
Reception
–
Coffee and Check-In
–
Some Probabilistic Uses of Dirichlet Eigenvectors
Persi Diaconis, Stanford University
–
Break
–
Independent Component Analysis: From Theory to Practice and Back
Santosh Vempala (Georgia Institute of Technology)
–
Break
–
Tensor Methods for Learning Latent Variable Models: Theory and Practice
Animashree Anandkumar, UC Irvine
–
Lunch
–
Random Walks on Directed Graphs
Fan Chung (UC San Diego)
–
Break
–
Random Embeddings, Matrix-valued Kernels and Deep Learning
Vikas Sindhwani, IBM T.J. Watson Research Center
–
Coffee and Check-In
–
A Statistical Model for Tensor Principal Component Analysis
Andrea Montanari (Stanford University)
–
Break
–
Graph Matching: Relax or Not?
Alex Bronstein, Tel Aviv University
–
Break
–
Random Walks on Simplicial Complexes and Isoperimetric Inequalities
Sayan Mukherjee, Duke University
–
Lunch
–
Connection Laplacian, Hodge Laplacian, and Tensor Laplacian of a Graph
Lek-Heng Lim (University of Chicago)
–
Break
–
Discussion and Open Problems
–
Coffee and Check-In
–
Spectral Algorithms for Learning Latent Variable Models
Sham Kakade, Microsoft Research New England
–
Break
–
Comparing the Theory and Practice of Spectral Algorithms to Combinatorial Flow Algorithms for Expander Ratio, Normalized Cut, Clustering and Conductance
Dorit Hochbaum (UC Berkeley)
–
Break
–
On the Estimation of the Cheeger Constant
Ery Arias-Castro, UC San Diego
–
Lunch
–
Applied Hodge Theory
Yuan Yao, Peking University
–
Break
–
The Hidden Convexity of Spectral Clustering
Luis Rademacher, Ohio State University
–
Break
–
Robust Spectral Diffusions for Data Applications
David Gleich (Purdue University)
–
Coffee and Check-In
–
Learning Functions and Sets with Spectral Regularization
Lorenzo Rosasco, Università di Genova and Massachusetts Institute of Technology
–
Break
–
Some Applications in Human Behavior Modeling
Jerry Zhu, University of Wisconsin-Madison
–
Break
–
Spectral Approaches to Nearest Neighbor Search
Alex Andoni (Columbia University)
–
Lunch
–
An Efficient Parallel Solver for SDD Linear Systems
Richard Peng, Massachusetts Institute of Technology
–
Break
–
Graph Based Processing of Big Images
Hui Han Chin, DSO National Laboratories