ML
2007
ACM
13 years 10 months ago
2007
ACM
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
ICML
2010
IEEE
14 years 1 days ago
2010
IEEE
When equipped with kernel functions, online learning algorithms are susceptible to the "curse of kernelization" that causes unbounded growth in the model size. To addres...
NIPS
2003
14 years 10 days ago
2003
We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed online learning algorithms asymptotically ...
NIPS
2008
14 years 12 days ago
2008
We present cutoff averaging, a technique for converting any conservative online learning algorithm into a batch learning algorithm. Most online-to-batch conversion techniques work...
AAAI
2008
14 years 1 months ago
2008
We examine online learning in the context of the Wisconsin Card Sorting Task (WCST), a task for which the concept acquisition strategies for human and other primates are well docu...
COLT
2006
Springer
14 years 2 months ago
2006
Springer
We describe a novel framework for the design and analysis of online learning algorithms based on the notion of duality in constrained optimization. We cast a sub-family of universa...
STOC
1997
ACM
14 years 3 months ago
1997
ACM
Abstract. We study online learning algorithms that predict by combining the predictions of several subordinate prediction algorithms, sometimes called “experts.” These simple a...
ILP
2005
Springer
14 years 4 months ago
2005
Springer
Online learning algorithms such as Winnow have received much attention in Machine Learning. Their performance degrades only logarithmically with the input dimension, making them us...
ALT
2008
Springer
14 years 8 months ago
2008
Springer
We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the ...
OSDI
2008
ACM
14 years 11 months ago
2008
ACM
Internet routing is mostly based on static information-it's dynamicity is limited to reacting to changes in topology. Adaptive performance-based routing decisions would not o...