Sciweavers

493 search results - page 8 / 99
» The oracle penalty method
Sort
View
ICML
2010
IEEE
13 years 10 months ago
Projection Penalties: Dimension Reduction without Loss
Dimension reduction is popular for learning predictive models in high-dimensional spaces. It can highlight the relevant part of the feature space and avoid the curse of dimensiona...
Yi Zhang 0010, Jeff Schneider
SIAMJO
2010
133views more  SIAMJO 2010»
13 years 7 months ago
Infeasibility Detection and SQP Methods for Nonlinear Optimization
This paper addresses the need for nonlinear programming algorithms that provide fast local convergence guarantees no matter if a problem is feasible or infeasible. We present an a...
Richard H. Byrd, Frank E. Curtis, Jorge Nocedal
ANOR
2010
87views more  ANOR 2010»
13 years 9 months ago
Image denoising via solution paths
Many image denoising methods can be characterized as minimizing "loss + penalty," where the "loss" measures the fidelity of the denoised image to the data, and ...
Li Wang, Ji Zhu
AML
2010
88views more  AML 2010»
13 years 9 months ago
Relativized Schnorr tests with universal behavior
A Schnorr test relative to some oracle A may informally be called "universal" if it covers all Schnorr tests. Since no true universal Schnorr test exists, such an A cann...
Nicholas Rupprecht