Sciweavers

3007 search results - page 27 / 602
» Linear Functional Fixed-points
Sort
View
UAI
2008
14 years 11 months ago
Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
Richard S. Sutton, Csaba Szepesvári, Alborz...
JAT
2010
71views more  JAT 2010»
14 years 8 months ago
Functions with prescribed best linear approximations
A common problem in applied mathematics is that of finding a function in a Hilbert space with prescribed best approximations from a finite number of closed vector subspaces. In ...
Patrick L. Combettes, Noli N. Reyes
NAACL
2010
14 years 7 months ago
Softmax-Margin CRFs: Training Log-Linear Models with Cost Functions
We describe a method of incorporating taskspecific cost functions into standard conditional log-likelihood (CLL) training of linear structured prediction models. Recently introduc...
Kevin Gimpel, Noah A. Smith
COR
2002
90views more  COR 2002»
14 years 9 months ago
Extremist vs. centrist decision behavior: quasi-convex utility functions for interactive multi-objective linear programming prob
This paper presents the fundamental theory and algorithms for identifying the most preferred alternative for a decision maker (DM) having a non-centrist (or extremist) preferentia...
Behnam Malakooti, Jumah E. Al-alwani
CORR
2011
Springer
192views Education» more  CORR 2011»
14 years 4 months ago
Distribution-Independent Evolvability of Linear Threshold Functions
Valiant’s (2007) model of evolvability models the evolutionary process of acquiring useful functionality as a restricted form of learning from random examples. Linear threshold ...
Vitaly Feldman