Sciweavers

236 search results - page 20 / 48
» Bias and Variance Approximation in Value Function Estimates
Sort
View
ICASSP
2010
IEEE
13 years 6 months ago
A transient analysis for the convex combination of two adaptive filters with transfer of coefficients
This paper proposes an improved model for the transient of convex combinations of adaptive filters. A previous model, based on a firstorder Taylor series approximation of the nonl...
Magno T. M. Silva, Vitor H. Nascimento, Jeró...
IJHPCA
2006
96views more  IJHPCA 2006»
13 years 8 months ago
On the User - Scheduler Dialogue: Studies of User-Provided Runtime Estimates and Utility Functions
Effective communication between user and scheduler is an important prerequisite to achieving a successful scheduling outcome from both parties' perspectives. In a grid or sta...
Cynthia Bailey Lee, Allan Snavely
UAI
2008
13 years 10 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...
IMC
2007
ACM
13 years 10 months ago
On optimal probing for delay and loss measurement
Packet delay and loss are two fundamental measures of performance. Using active probing to measure delay and loss typically involves sending Poisson probes, on the basis of the PA...
François Baccelli, Sridhar Machiraju, Darry...
CORR
2004
Springer
103views Education» more  CORR 2004»
13 years 8 months ago
Online convex optimization in the bandit setting: gradient descent without a gradient
We study a general online convex optimization problem. We have a convex set S and an unknown sequence of cost functions c1, c2, . . . , and in each period, we choose a feasible po...
Abraham Flaxman, Adam Tauman Kalai, H. Brendan McM...