Sciweavers

2623 search results - page 239 / 525
» Universal Learning Theory
Sort
View
DSMML
2004
Springer
16 years 1 days ago
Can Gaussian Process Regression Be Made Robust Against Model Mismatch?
Learning curves for Gaussian process (GP) regression can be strongly affected by a mismatch between the ‘student’ model and the ‘teacher’ (true data generation process), e...
Peter Sollich
COCO
2001
Springer
149views Algorithms» more  COCO 2001»
15 years 11 months ago
Quantum versus Classical Learnability
Motivated by recent work on quantum black-box query complexity, we consider quantum versions of two wellstudied models of learning Boolean functions: Angluin’s model of exact le...
Rocco A. Servedio, Steven J. Gortler
EUROCOLT
1999
Springer
15 years 11 months ago
Regularized Principal Manifolds
Many settings of unsupervised learning can be viewed as quantization problems — the minimization of the expected quantization error subject to some restrictions. This allows the ...
Alex J. Smola, Robert C. Williamson, Sebastian Mik...
WIKIS
2009
ACM
15 years 11 months ago
Understanding learning: the Wiki way
Learning “the wiki way”, learning through wikis is a form of selfregulated learning that is independent of formal learning settings and takes place in a community of knowledge...
Joachim Kimmerle, Johannes Moskaliuk, Ulrike Cress
NIPS
2007
15 years 8 months ago
The Tradeoffs of Large Scale Learning
This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms. The analysis shows distinct tradeoffs for...
Léon Bottou, Olivier Bousquet