… To address this issue, we propose the multitask generalized eigenvalue program (MTGEP)
algorithm, which jointly solves K related GEPs. By leveraging knowledge of other GEPs, we …

… nonparametric multitask learning … eigenvalues and corresponding eigenfunctions of a
predefined integral operator on an RKHS. In our method, we formulate our objective for multitask …

… to use only matrices of moderate size (mostly N in the range of 200 to 500), since the
programs embedding the eigenvalue problems require a certain amount of memory themselves. …

… We leverage this issue by casting the PCA into a multitask framework, and doing so, we
show how to solve simultaneously several related PCA problems. Hence, we propose a novel …

… F-related to study the generalizability of multitask classification based on the generalized
Vapnik–Chervonenkis (VC) dimension. Maurer [14] presented the generalization bounds for …

… , our approach—multitask relationship learning (MTRL)—can … symmetric multitask learning
setting and then generalize it to … MTRL and some existing multitask learning methods. …

… multitask models have been proposed. In order to identify an effective multitask model for
a given multitask problem, we propose a learning framework called Learning to MultiTask (…

… Motivated by our application to the M/EEG inverse problem (see Section 5.3, we present all
the results in a multi-task setting. These results are still valid for single task problems (q = 1), …

Learning the common structure shared by a set of supervised tasks is an important practical
and theoretical problem. Knowledge of this structure may lead to bet-ter generalization …

Often, tasks are collected for multi-task learning (MTL) because they share similar feature
structures. Based on this observation, in this paper, we present novel algorithm-dependent …