NIPS 2011 Sparse Representation & Low-rank Approximation Workshop: Fast global convergence...
1,002 views · Published 8 February 2012 · 36:59 · Indexed 8 November 2026
Channel: Google TechTalks · 2012 · Science & Technology
Sparse Representation and Low-rank Approximation Workshop at NIPS 2011 Invited Talk: Computation meets Statistics: Fast global convergence for high-dimensional statistical recovery by Martin Wainwright, University of California at Berkeley, Department of Statistics and EECS Abstract: Many statistical estimators are based on convex optimization problems formed by the weighted sum of a loss function with a norm-based regularizer. Particular examples include $\ell_1$-based methods for sparse vectors, nuclear norm for low-rank matrices, and various combinations thereof for matrix decomposition. In this talk, we describe an interesting connection between computational and statistical efficiency, in particular showing that the same conditions that guarantee that an estimator has low statistical error can also be used to certify fast convergence of first-order optimization methods up to statistical precision.
More from this channel
-
34:17
Thinglink - A Free Product Code for Creative Work
-
32:48
Thinking Beyond Borders
-
44:29
Understanding Urban Environments Through the Use of...
-
46:05
Customer Centric Web Decision Making
-
46:04
Customizable Scalable Compute Intensive Stream Queries
-
51:26
All The Government's Information
-
41:35
Combining Discriminative Features to Infer Complex...
-
59:42
Dimensions of Reputation in Electronic Markets