Workshops

Fall 2014

Spectral Algorithms: From Theory to Practice

Oct 27, 2014 to Oct 31, 2014

Return to event »

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

All events take place in the Calvin Lab Auditorium.

Monday, October 27th, 2014
9:00 am – 9:20 am		Coffee and Check-In
9:20 am – 9:30 am		Opening Remarks
9:30 am – 10:15 am		Topic Modeling: A Provable Spectral Method Ravi Kannan, Microsoft Research India
10:15 am – 10:45 am		Break
10:45 am – 11:30 am		Exact Recovery via Convex Relaxations Moses Charikar, Princeton University
11:30 am – 12:00 pm		Break
12:00 pm – 12:45 pm		The Impact of Regularization in Spectral Clustering Bin Yu, UC Berkeley
12:45 pm – 2:30 pm		Lunch
2:30 pm – 3:15 pm		Multiscale Analysis on and of Graphs Mauro Maggioni, Duke University
3:15 pm – 3:45 pm		Break
3:45 pm – 4:30 pm		Multiresolution Graph Models Risi Kondor, University of Chicago
4:45 pm – 6:00 pm		Reception

Tuesday, October 28th, 2014
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:15 am		Some Probabilistic Uses of Dirichlet Eigenvectors Persi Diaconis, Stanford University
10:15 am – 10:45 am		Break
10:45 am – 11:30 am		Independent Component Analysis: From Theory to Practice and Back Santosh Vempala, Georgia Institute of Technology
11:30 am – 12:00 pm		Break
12:00 pm – 12:45 pm		Tensor Methods for Learning Latent Variable Models: Theory and Practice Animashree Anandkumar, UC Irvine
12:45 pm – 2:30 pm		Lunch
2:30 pm – 3:15 pm		Random Walks on Directed Graphs Fan Chung, UC San Diego
3:15 pm – 3:45 pm		Break
3:45 pm – 4:30 pm		Random Embeddings, Matrix-valued Kernels and Deep Learning Vikas Sindhwani, IBM T.J. Watson Research Center

Wednesday, October 29th, 2014
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:15 am		A Statistical Model for Tensor Principal Component Analysis Andrea Montanari, Stanford University
10:15 am – 10:45 am		Break
10:45 am – 11:30 am		Graph Matching: Relax or Not? Alex Bronstein, Tel Aviv University
11:30 am – 12:00 pm		Break
12:00 pm – 12:45 pm		Random Walks on Simplicial Complexes and Isoperimetric Inequalities Sayan Mukherjee, Duke University
12:45 pm – 2:30 pm		Lunch
2:30 pm – 3:15 pm		Connection Laplacian, Hodge Laplacian, and Tensor Laplacian of a Graph Lek-Heng Lim, University of Chicago
3:15 pm – 3:45 pm		Break
3:45 pm – 4:30 pm		Discussion and Open Problems

Thursday, October 30th, 2014
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:15 pm		Spectral Algorithms for Learning Latent Variable Models Sham Kakade, Microsoft Research New England
10:15 am – 10:45 am		Break
10:45 am – 11:30 am		Comparing the Theory and Practice of Spectral Algorithms to Combinatorial Flow Algorithms for Expander Ratio, Normalized Cut, Clustering and Conductance Dorit Hochbaum, UC Berkeley
11:30 am – 12:00 pm		Break
12:00 pm – 12:45 pm		On the Estimation of the Cheeger Constant Ery Arias-Castro, UC San Diego
12:45 pm – 2:15 pm		Lunch
2:15 pm – 3:00 pm		Applied Hodge Theory Yuan Yao, Peking University
3:00 pm – 3:15 pm		Break
3:15 pm – 4:00 pm		The Hidden Convexity of Spectral Clustering Luis Rademacher, Ohio State University
4:00 pm – 4:15 pm		Break
4:15 pm – 5:00 pm		Robust Spectral Diffusions for Data Applications David Gleich, Purdue University

Friday, October 31st, 2014
9:00 am – 9:30 am		Coffee and Check-In
9:30 am – 10:15 am		Learning Functions and Sets with Spectral Regularization Lorenzo Rosasco, Università di Genova and Massachusetts Institute of Technology
10:15 am – 10:45 am		Break
10:45 am – 11:30 am		Some Applications in Human Behavior Modeling Jerry Zhu, University of Wisconsin-Madison
11:30 am – 12:00 pm		Break
12:00 pm – 12:45 pm		Spectral Approaches to Nearest Neighbor Search Alexandr Andoni
12:45 pm – 2:30 pm		Lunch
2:30 pm – 3:15 pm		An Efficient Parallel Solver for SDD Linear Systems Richard Peng, Massachusetts Institute of Technology
3:15 pm – 3:45 pm		Break
3:45 pm – 4:30 pm		Graph Based Processing of Big Images Hui Han Chin, DSO National Laboratories