Learning Similarity with Operator-valued Large-margin Classifiers
The Journal of Machine Learning Research
Unsupervised slow subspace-learning from stationary processes
Theoretical Computer Science
An Algorithm for Transfer Learning in a Heterogeneous Environment
ECML PKDD '08 Proceedings of the 2008 European Conference on Machine Learning and Knowledge Discovery in Databases - Part I
Convex multi-task feature learning
Machine Learning
Transfer bounds for linear feature learning
Machine Learning
Multi-resolution learning for knowledge transfer
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
When Is There a Representer Theorem? Vector Versus Matrix Regularizers
The Journal of Machine Learning Research
The Journal of Machine Learning Research
A novel learning approach to multiple tasks based on boosting methodology
Pattern Recognition Letters
Linear Algorithms for Online Multitask Classification
The Journal of Machine Learning Research
Multitask Sparsity via Maximum Entropy Discrimination
The Journal of Machine Learning Research
Transfer learning with adaptive regularizers
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part III
Unsupervised slow subspace-learning from stationary processes
ALT'06 Proceedings of the 17th international conference on Algorithmic Learning Theory
The rademacher complexity of linear transformation classes
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Regularization techniques for learning with matrices
The Journal of Machine Learning Research
| Hi-index | 0.00 |
We give dimension-free and data-dependent bounds for linear multi-task learning where a common linear operator is chosen to preprocess data for a vector of task specific linear-thresholding classifiers. The complexity penalty of multi-task learning is bounded by a simple expression involving the margins of the task-specific classifiers, the Hilbert-Schmidt norm of the selected preprocessor and the Hilbert-Schmidt norm of the covariance operator for the total mixture of all task distributions, or, alternatively, the Frobenius norm of the total Gramian matrix for the data-dependent version. The results can be compared to state-of-the-art results on linear single-task learning.