Decision theoretic generalizations of the PAC model for neural net and other learning applications
Information and Computation
Learning internal representations
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Learning in Neural Networks: Theoretical Foundations
Learning in Neural Networks: Theoretical Foundations
Model Selection and Error Estimation
Machine Learning
Rademacher and gaussian complexities: risk bounds and structural results
The Journal of Machine Learning Research
Improving SVM accuracy by training on auxiliary data sources
ICML '04 Proceedings of the twenty-first international conference on Machine learning
Algorithmic Stability and Meta-Learning
The Journal of Machine Learning Research
Rademacher penalties and structural risk minimization
IEEE Transactions on Information Theory
Good learners for evil teachers
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Domain adaptation from multiple sources via auxiliary classifiers
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Multiple information sources cooperative learning
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Multiple source adaptation and the Rényi divergence
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Predictive distribution matching SVM for multi-domain learning
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part I
Algorithmic trading strategy optimization based on mutual information entropy based clustering
ISICA'10 Proceedings of the 5th international conference on Advances in computation and intelligence
Logistic regression for transductive transfer learning from multiple sources
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications - Volume Part II
Multi-view transfer learning with a large margin approach
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Local feature based tensor kernel for image manifold learning
PAKDD'11 Proceedings of the 15th Pacific-Asia conference on Advances in knowledge discovery and data mining - Volume Part II
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part III
A case study on meta-generalising: a Gaussian processes approach
The Journal of Machine Learning Research
Investigating Multi-View Differential Evolution for solving constrained engineering design problems
Expert Systems with Applications: An International Journal
Multi-source learning with block-wise missing data for Alzheimer's disease prediction
Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Selective sampling and active learning from single and multiple teachers
The Journal of Machine Learning Research
Hi-index | 0.01 |
We consider the problem of learning accurate models from multiple sources of "nearby" data. Given distinct samples from multiple data sources and estimates of the dissimilarities between these sources, we provide a general theory of which samples should be used to learn models for each source. This theory is applicable in a broad decision-theoretic learning framework, and yields general results for classification and regression. A key component of our approach is the development of approximate triangle inequalities for expected loss, which may be of independent interest. We discuss the related problem of learning parameters of a distribution from multiple data sources. Finally, we illustrate our theory through a series of synthetic simulations.