NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Randomized Smoothing for...

Channel:
United States Google TechTalks
Subscribers:
348,000
Published on ● Video Link: https://www.youtube.com/watch?v=A15BKtP_JFY


Duration: 23:31
2,075 views
8

Big Learning Workshop: Algorithms, Systems, and Tools for Learning at Scale at NIPS 2011

Invited Talk: Randomized Smoothing for (Parallel) Stochastic Optimization by John Duchi

John Duchi is currently a PhD candidate in computer science at Berkeley, where he started in the fall of 2008. He works in the Statistical Artificial Intelligence Lab (SAIL) under the joint supervision of Mike Jordan and Martin Wainwright. John is currently supported by an NDSEG fellowship and starting next year, he will be supported by Facebook, who have generously awarded him a Facebook Fellowship.

Abstract: By combining randomized smoothing techniques with accelerated gradient methods, we obtain convergence rates for stochastic optimization procedures, both in expectation and with high probability, that have optimal dependence on the variance of the gradient estimates. To the best of our knowledge, these are the first variance-based rates for non-smooth optimization. A combination of our techniques with recent work on decentralized optimization yields order-optimal parallel stochastic optimization algorithms. We give applications of our results to statistical machine learning problems, providing experimental results demonstrating the effectiveness of our algorithms.



Other Videos By Google TechTalks


2012-02-14Agile C++ with Supporting Eclipse CDT Plug-ins
2012-02-14Santa Tracker - 1.6 Million Requests per Second
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Spark: In-Memory Cluster...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Real time data...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Hazy - Making Data-driven...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Block splitting for...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: No-U-Turn Sampler...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Graphlab 2...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Graphlab 2 Tutorial
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Large-Scale Matrix...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Randomized Smoothing for...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Machine Learning's Role...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Fast Cross-Validation...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: High-Performance Computing...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Towards Human Behavior...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Parallelizing Training ...
2012-02-13NIPS 2011 Big Learning Workshop - Algorithms, Systems, & Tools for Learning at Scale: NeuFlow...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Bootstrapping Big Data...
2012-02-13NIPS 2011 Big Learning - Algorithms, Systems, & Tools Workshop: Big Machine Learning...
2012-02-09NIPS 2011 Sparse Representation & Low-rank Approximation Workshop: Dictionary-Dependent Penalties...
2012-02-09NIPS 2011 Sparse Representation & Low-rank Approximation Workshop: Robust Sparse Analysis...


Tags:
new
bigml
d2
duchi