Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
ML
2007
ACM
131views Machine Learning» more  ML 2007»
11 years 1 months ago
A primal-dual perspective of online learning algorithms
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...
Shai Shalev-Shwartz, Yoram Singer
ICML
2010
IEEE
11 years 2 months ago
Multi-Class Pegasos on a Budget
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...
Zhuang Wang, Koby Crammer, Slobodan Vucetic
NIPS
2003
11 years 2 months ago
Large Scale Online Learning
We consider situations where training data is abundant and computing resources are comparatively scarce. We argue that suitably designed online learning algorithms asymptotically ...
Léon Bottou, Yann LeCun
NIPS
2008
11 years 2 months ago
From Online to Batch Learning with Cutoff-Averaging
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...
Ofer Dekel
AAAI
2008
11 years 3 months ago
Online Learning in Monkeys
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...
Xiaojin Zhu, Michael Coen, Shelley Prudom, Ricki C...
COLT
2006
Springer
11 years 5 months ago
Online Learning Meets Optimization in the Dual
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...
Shai Shalev-Shwartz, Yoram Singer
STOC
1997
ACM
97views Algorithms» more  STOC 1997»
11 years 5 months ago
Using and Combining Predictors That Specialize
Abstract. We study online learning algorithms that predict by combining the predictions of several subordinate prediction algorithms, sometimes called “experts.” These simple a...
Yoav Freund, Robert E. Schapire, Yoram Singer, Man...
ILP
2005
Springer
11 years 7 months ago
Online Closure-Based Learning of Relational Theories
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...
Frédéric Koriche
ALT
2008
Springer
11 years 10 months ago
Learning with Continuous Experts Using Drifting Games
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 ...
Indraneel Mukherjee, Robert E. Schapire
OSDI
2008
ACM
12 years 1 months ago
From Optimization to Regret Minimization and Back Again
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...
Ioannis C. Avramopoulos, Jennifer Rexford, Robert ...
books