Sciweavers

5214 search results - page 120 / 1043
» The Online Specialization Problem
Sort
View
AAAI
1998
13 years 10 months ago
Applying Online Search Techniques to Continuous-State Reinforcement Learning
In this paper, we describe methods for e ciently computing better solutions to control problems in continuous state spaces. We provide algorithms that exploit online search to boo...
Scott Davies, Andrew Y. Ng, Andrew W. Moore
SIAMSC
2010
132views more  SIAMSC 2010»
13 years 7 months ago
New Algorithms for Optimal Online Checkpointing
Frequently, the computation of derivatives for optimizing time-dependent problems is based on the integration of the adjoint differential equation. For this purpose, the knowledge...
Philipp Stumm, Andrea Walther
ANOR
2010
112views more  ANOR 2010»
13 years 7 months ago
Online stochastic optimization under time constraints
This paper considers online stochastic optimization problems where uncertainties are characterized by a distribution that can be sampled and where time constraints severely limit t...
Pascal Van Hentenryck, Russell Bent, Eli Upfal
JMLR
2010
161views more  JMLR 2010»
13 years 3 months ago
Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization
We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning...
Lin Xiao
KDD
2012
ACM
292views Data Mining» more  KDD 2012»
11 years 11 months ago
Online allocation of display ads with smooth delivery
Display ads on the Internet are often sold in bundles of thousands or millions of impressions over a particular time period, typically weeks or months. Ad serving systems that ass...
Anand Bhalgat, Jon Feldman, Vahab S. Mirrokni