Random Embeddings, Matrix-valued Kernels and Deep Learning

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=9Mdi7ig5Q2k


Duration: 55:46
1,461 views
6

Vikas Sindhwani, IBM T.J. Watson Research Center
Spectral Algorithms: From Theory to Practice
http://simons.berkeley.edu/talks/vikas-sindhwani-2014-10-28



Other Videos By Simons Institute for the Theory of Computing


2014-11-03Autocatalytic Sets and Models of Early Life
2014-11-03Some Applications in Human Behavior Modeling
2014-11-03Comparing the Theory and Practice of Spectral Algorithms to Combinatorial Flow Algorithms for ...
2014-11-03Spectral Approaches to Nearest Neighbor Search
2014-11-03Learning Functions and Sets with Spectral Regularization
2014-11-03Graph Matching: Relax or Not?
2014-11-03Connection Laplacian, Hodge Laplacian, and Tensor Laplacian of a Graph
2014-11-03Independent Component Analysis: From Theory to Practice and Back
2014-11-03Topic Modeling: A Provable Spectral Method
2014-11-03Random Walks on Directed Graphs
2014-11-03Random Embeddings, Matrix-valued Kernels and Deep Learning
2014-11-03On the Estimation of the Cheeger Constant
2014-11-03Tensor Methods for Learning Latent Variable Models: Theory and Practice
2014-11-03Robust Spectral Diffusions for Data Applications
2014-11-03Multiresolution Graph Models
2014-10-21A Theory of Complexity, Condition and Roundoff
2014-10-21Bertini_real: Software for Real Algebraic Sets
2014-10-21Characterization of the Affine Solutions of Sparse Polynomial Systems
2014-10-21Advances in Numerical Algebraic Geometry with Applications
2014-10-21Numerical Algebraic Geometry for Maximum Likelihood Estimation
2014-10-21Identifiability of Viscoelastic Mechanical Systems


Tags:
Simons Institute
UC Berkeley
computer science
theory of computing
Algorithmic Spectral Graph Theory
Vikas Sindhwani