Sciweavers

376 search results - page 10 / 76
» On the Advice Complexity of Online Problems
Sort
View
CORR
2010
Springer
101views Education» more  CORR 2010»
14 years 11 months ago
Online Learning: Random Averages, Combinatorial Parameters, and Learnability
We develop a theory of online learning by defining several complexity measures. Among them are analogues of Rademacher complexity, covering numbers and fatshattering dimension fro...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
AOSD
2008
ACM
15 years 1 months ago
AJANA: a general framework for source-code-level interprocedural dataflow analysis of AspectJ software
Aspect-oriented software presents new challenges for the designers of static analyses. Our work aims to establish systematic foundations for dataflow analysis of AspectJ software....
Guoqing Xu, Atanas Rountev
JMLR
2012
13 years 2 months ago
Multi Kernel Learning with Online-Batch Optimization
In recent years there has been a lot of interest in designing principled classification algorithms over multiple cues, based on the intuitive notion that using more features shou...
Francesco Orabona, Jie Luo, Barbara Caputo
IOR
2002
179views more  IOR 2002»
14 years 11 months ago
Decision Analysis: A Personal Account of How It Got Started and Evolved
Then these analytically motivated abstractions were gradually made more intricate as the body of mathematical techniques grew. The trend went from elementary analysis of complex, i...
Howard Raiffa
CORR
2007
Springer
169views Education» more  CORR 2007»
14 years 11 months ago
Algorithmic Complexity Bounds on Future Prediction Errors
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true d...
Alexey V. Chernov, Marcus Hutter, Jürgen Schm...