Sciweavers

77 search results - page 4 / 16
» Efficient bandit algorithms for online multiclass prediction
Sort
View
ALT
2005
Springer
14 years 3 months ago
Defensive Universal Learning with Experts
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...
Jan Poland, Marcus Hutter
JMLR
2008
137views more  JMLR 2008»
13 years 6 months ago
Online Learning of Complex Prediction Problems Using Simultaneous Projections
We describe and analyze an algorithmic framework for online classification where each online trial consists of multiple prediction tasks that are tied together. We tackle the prob...
Yonatan Amit, Shai Shalev-Shwartz, Yoram Singer
COMCOM
2004
117views more  COMCOM 2004»
13 years 6 months ago
Dynamic bandwidth allocation in multi-class connection-oriented networks
Multi-class network is becoming a more attractive solution to provide Quality-of-Service guarantee, as more quality-demanding applications are emerging. This research considers ne...
Samer Taha, Mohsen Kavehrad
ICDE
1999
IEEE
150views Database» more  ICDE 1999»
14 years 8 months ago
Managing Distributed Memory to Meet Multiclass Workload Response Time Goals
In this paper we present an online method for managing a goaloriented buffer partitioning in the distributed memory of a network of workstations. Our algorithm implements a feedba...
Arnd Christian König, Markus Sinnwell
JMLR
2006
116views more  JMLR 2006»
13 years 6 months ago
Step Size Adaptation in Reproducing Kernel Hilbert Space
This paper presents an online support vector machine (SVM) that uses the stochastic meta-descent (SMD) algorithm to adapt its step size automatically. We formulate the online lear...
S. V. N. Vishwanathan, Nicol N. Schraudolph, Alex ...