Sciweavers

4277 search results - page 207 / 856
» On Multiple Linear Approximations
Sort
View
CORR
2010
Springer
119views Education» more  CORR 2010»
14 years 11 months ago
Dynamic Policy Programming
In this paper, we consider the problem of planning and learning in the infinite-horizon discounted-reward Markov decision problems. We propose a novel iterative direct policysearc...
Mohammad Gheshlaghi Azar, Hilbert J. Kappen
TSP
2010
14 years 5 months ago
Quasi-interpolation by means of filter-banks
We consider the problem of approximating a regular function f(t) from its samples, f(nT), taken in a uniform grid. Quasi-interpolation schemes approximate f(t) with a dilated versi...
Gerardo Pérez-Villalón
AMC
2006
105views more  AMC 2006»
14 years 11 months ago
Stable numerical methods for conservation laws with discontinuous flux function
We develop numerical methods for solving nonlinear equations of conservation laws with flux function that depends on discontinuous coefficients. Using a relaxation approximation, ...
Mohammed Seaïd
MOC
1998
94views more  MOC 1998»
14 years 10 months ago
Analysis of third-order methods for secular equations
Third-order numerical methods are analyzed for secular equations. These equations arise in several matrix problems and numerical linear algebra applications. A closer look at an ex...
A. Melman
SIAMJO
2010
125views more  SIAMJO 2010»
14 years 5 months ago
Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints
We study the problem of minimizing the expected loss of a linear predictor while constraining its sparsity, i.e., bounding the number of features used by the predictor. While the r...
Shai Shalev-Shwartz, Nathan Srebro, Tong Zhang