A Probabilistic Model for Dirty Multi-task Feature Selection

By Daniel Hernández-Lobato, José Miguel Hernández-Lobato, Zoubin Ghahramani. 2015

42 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “The difference between [16] and [17] is that in [16], the horseshoeprior is generalized to learn feature covariance, while in [17], the horseshoe prior is used as a basic prior and the whole model is to identify outlier tasks in a way different from [15].”
A Survey on Multi-Task Learning (2017, neutral): “ correlations. When C becomes an identity matrix which means that features are independent, this prior degenerates to the horseshoe prior which can induce sparse estimations. Hern´andez-Lobato et al. [43] propose a probabilistic model based on the horseshoe prior as: P(w ji) = h ˇ(w ji) ji1 ji 0 i z”
Learning Multiple Tasks with Multilinear Relationship Networks (2015, methodology): “‘ D o ‘ +TD i ‘ D o ‘ )). Finally, the cost for updating task relationship tensors in multilayers is O( P ‘2L (T 2Di ‘ D o ‘ +T 3)). 4.3 Discussion Our work contrasts from prior relationship learning [31, 32, 16] and multi-task deep learning [26, 33, 7, 29] methods in two key aspects. (1) Tensor nor”
Feature Selection Based on Structured Sparsity: A Comprehensive Study (2017, background): “There are some closely related areas for specific tasks with rich literature [105], [106].”
Learning Multiple Tasks with Deep Relationship Networks (2015, methodology): “There are generally two categories of approaches: (1) multi-task feature learning, which learns a shared feature representation such that the distribution shift across different tasks can be reduced [1, 2, 6, 5, 16]; and (2) multi-task relationship learning, which explicitly models the task relation”