Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

10

COLT
2005
Springer

favoriteEmaildiscussreport

109views Machine Learning» more COLT 2005»

Data Dependent Concentration Bounds for Sequential Prediction Algorithms

13 years 6 months ago

Data Dependent Concentration Bounds for Sequential Prediction Algorithms

Download stat.rutgers.edu

Abstract. We investigate the generalization behavior of sequential prediction (online) algorithms, when data are generated from a probability distribution. Using some newly developed probability inequalities, we are able to bound the total generalization performance of a learning algorithm in terms of its observed total loss. Consequences of this analysis will be illustrated with examples.

Tong Zhang

Real-time Traffic

COLT 2005 | Generalization Behavior | Machine Learning | Observed Total Loss | Total Generalization Performance |

claim paper

Related Content

» Universal Switching Linear Least Squares Prediction

» A Randomized Online Learning Algorithm for Better Variance Control

» Scanning and Sequential Decision Making for Multidimensional Data Part II The Noisy Case

» Bounded approximate decentralised coordination via the maxsum algorithm

» Online Learning in Case of Unbounded Losses Using Follow the Perturbed Leader Algorithm

» A Genetic Algorithm Method to Assimilate Sensor Data for a Toxic Contaminant Release

» Modeling of concurrent web sessions with bounded inconsistency in shared data

» Hierarchy Construction Schemes Within the Scale Set Framework

» Learning Markov networks maximum bounded treewidth graphs

Post Info
More Details (n/a)

Added	13 Oct 2010
Updated	13 Oct 2010
Type	Conference
Year	2005
Where	COLT
Authors	Tong Zhang

Comments (0)