Sciweavers

2477 search results - page 265 / 496
» Approximate extended formulations
Sort
View
ICML
2010
IEEE
15 years 5 months ago
Feature Selection as a One-Player Game
This paper formalizes Feature Selection as a Reinforcement Learning problem, leading to a provably optimal though intractable selection policy. As a second contribution, this pape...
Romaric Gaudel, Michèle Sebag
ADCM
2007
59views more  ADCM 2007»
15 years 4 months ago
Gabor frames by sampling and periodization
By sampling the window of a Gabor frame for L2 (R) belonging to Feichtinger’s algebra, S0(R), one obtains a Gabor frame for l2 (Z). In this article we present a survey of results...
Peter L. Søndergaard
CORR
2010
Springer
116views Education» more  CORR 2010»
15 years 4 months ago
Estimation with Random Linear Mixing, Belief Propagation and Compressed Sensing
Abstract--We apply Guo and Wang's relaxed belief propagation (BP) method to the estimation of a random vector from linear measurements followed by a componentwise probabilisti...
Sundeep Rangan
CORR
2010
Springer
166views Education» more  CORR 2010»
15 years 4 months ago
The dynamics of message passing on dense graphs, with applications to compressed sensing
`Approximate message passing' algorithms proved to be extremely effective in reconstructing sparse signals from a small number of incoherent linear measurements. Extensive num...
Mohsen Bayati, Andrea Montanari
ENTCS
2006
118views more  ENTCS 2006»
15 years 4 months ago
An Operational Domain-theoretic Treatment of Recursive Types
We develop a domain theory for treating recursive types with respect to contextual equivalence. The principal approach taken here deviates from classical domain theory in that we ...
Weng Kin Ho