Sciweavers

835 search results - page 12 / 167
» Adaptive Bound Optimization for Online Convex Optimization
Sort
View
JMLR
2010
143views more  JMLR 2010»
13 years 6 months ago
A Quasi-Newton Approach to Nonsmooth Convex Optimization Problems in Machine Learning
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by ge...
Jin Yu, S. V. N. Vishwanathan, Simon Günter, ...
MP
2007
76views more  MP 2007»
13 years 7 months ago
Universal duality in conic convex optimization
Given a primal-dual pair of linear programs, it is well known that if their optimal values are viewed as lying on the extended real line, then the duality gap is zero, unless both...
Simon P. Schurr, André L. Tits, Dianne P. O...
TSP
2008
100views more  TSP 2008»
13 years 7 months ago
Optimal Two-Stage Search for Sparse Targets Using Convex Criteria
We consider the problem of estimating and detecting sparse signals over a large area of an image or other medium. We introduce a novel cost function that captures the tradeoff bet...
Eran Bashan, Raviv Raich, Alfred O. Hero III
CGO
2009
IEEE
14 years 2 months ago
Scenario Based Optimization: A Framework for Statically Enabling Online Optimizations
Abstract—Online optimization allows the continuous restructuring and adaptation of an executing application using live information about its execution environment. The further ad...
Jason Mars, Robert Hundt
EMMCVPR
2011
Springer
12 years 7 months ago
Optimality Bounds for a Variational Relaxation of the Image Partitioning Problem
Variational relaxations can be used to compute approximate minimizers of optimal partitioning and multiclass labeling problems on continuous domains. While the resulting relaxed co...
Jan Lellmann, Frank Lenzen, Christoph Schnörr