Workshop
Multiresolution methods for large-scale learning
Inderjit S Dhillon · Risi Kondor · Rob Nowak · Michael O'Neil · Nedelina Teneva

Sat Dec 12th 08:30 AM -- 06:30 PM @ 511 c
Event URL: http://people.cs.uchicago.edu/~risi/NIPS15workshop/index.html »

There is a surge of new work at the intersection of multiresolution/multiscale methods and machine learning:

- Multiresolution (wavelets) on graphs is one of the hottest topics in harmonic analysis, with important implications for learning on graphs and semi-spervised learning.
- Hierarchical matrices (HODLR, H, H2 and HSS matrices), a very active area in numerical analysis, have also been shown to be effective in Gaussian processes inference.
- Scattering networks are a major breakthrough, and combine ideas from wavelet analysis and deep learning.
- Multiscale graph models are ever more popular because they can capture important structures in real world networks.
- Multiscale matrix decompositions and multiresolution matrix factorizations, mirroring some features of algebraic multigrid methods, are gaining traction in large scale data applications.

The goal of this workshop is to bring together leading researchers from Harmonic Analysis, Signal Processing, Numerical Analysis, and Machine Learning, to explore the synergies between all the above lines of work.

09:00 AM Random sampling of bandlimited signals on graphs (Talk) Pierre Vandergheynst
09:40 AM Multiresolution Matrix Factorization (Talk) Risi Kondor
10:30 AM Beyond Nodes and Edges: Multiresolution Models of Complex Networks (Talk) Austin Benson
11:00 AM Challenges in Multiresolution Methods for Graph-based Learning (Talk) Michael W Mahoney
11:30 AM Probabilistic Theory of Deep Learning (talk) Richard Baraniuk
11:50 AM Hierarchical Decomposition of Kernel Matrices (Talk) Bill March
02:00 PM Multigrid-inspired Methods for Networks (Talk) Ilya Safro
02:30 PM Fast Direct Methods for Gaussian Processes (Talk) Mike O'Neil
03:00 PM Approximating Gaussian Processes with H^2 Matrices (Talk) Jochen Garcke
03:20 PM A Multiresolution Approach for Tensor Factorization (Talk) Kunal Srivastava
03:40 PM Multiresolution analysis for the statistical analysis of incomplete rankings (Talk) Eric Sibony
04:30 PM Structured Sparsity and convex optimization (Talk) Francis Bach
05:00 PM Scaling Phenomena in Stochastic Topology (Talk) Sayan Mukherjee

Author Information

Inderjit S Dhillon (University of Texas at Austin)
Risi Kondor (The University of Chicago)
Rob Nowak (Wisconsin)
Mike O'Neil (New York University)
Nedelina Teneva (The University of Chicago)

More from the Same Authors