Learning Multiple Tasks with a Sparse Matrix-Normal Penalty

By Yi Zhang, Jeff Schneider. 2010

132 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “A model similar to the MTRL method is proposed in [49] by assigning a prior on W as W ∼ MN (0, 1, 2), and it learns the sparse inverse of 1 and 2.”
Learning Task Grouping and Overlap in Multi-task Learning (2012, background): “There also exist probabilistic models which attempt to learn full task covariance matrix and use it in learning of predictor functions (Zhang & Yeung, 2010b;a; Zhang & Schneider, 2010; Archambeau et al., 2011).”
Multi-Task CNN Model for Attribute Prediction (2015, methodology): “While Max-margin is known by its discriminative power, Bayesian is more flexible and thus better suited to engage any a priori or performance inference [31].”
Learning Multi-Level Task Groups in Multi-Task Learning (2015, background): “All rights reserved. and Xu 2010; Zhang and Schneider 2010; Zhang and Yeung 2010; Zhang 2013; Zhang and Yeung 2014), and some assume the task structure is hierarchical (Daumé III 2009; Jalali et al. 2010; Görnitz et al. 2011; Lozano and Swirszcz 2012; Zweig and Weinshall 2013).”
Interactive Multi-task Relationship Learning (2016, methodology): “To address this problem, the multi-task relationship learning (MTRL) approaches [32, 14, 31] are studied to learn the task relationship in the form of a task covariance matrix from the data, representing how similar are Fig.”
Generalized Dictionary for Multitask Learning with Boosting (2016, methodology): “Task relatedness has also been modeled by correlations [Zhang and Yeung, 2010; Zhang and Schneider, 2010] or tree structures [Kim and Xing, 2010].”
A Regularization Approach to Learning Task Relationships in Multitask Learning (2014, methodology): “Moreover, to improve the interpretability, the multitask feature selection methods [Obozinski et al. 2006; Obozinski et al. 2010; Zhang et al. 2010] are to select one subset of the original features by utilizing some sparsity-inducing priors (e.g., l 1 / l p norm ( p > 1)).”
Efficient Multitask Feature and Relationship Learning (2017, methodology): “As another baseline, we also compare our method with the multilin-ear relationship network (Long et al., 2017), which can be understood as an extension of the MTFRL method using neural networks ( MTFRL-NN ).”
Reconciling meta-learning and continual learning with online mixtures of tasks (2018, background): “Moreover, explicitly estimating relatedness between tasks has the potential to aid the efficacy of a meta-learning algorithm by modulating both positive and negative transfer [52, 59, 45, 61], and by identifying outlier tasks that require a more significant degree of adaptation [56, 23].”
Learning Sparse Task Relations in Multi-Task Learning (2017, methodology): “…trace of Ω but also learns sparse task relations via the penalization of the off-diagonal entries in Ω. Note that problem (3) is different from the methods proposed in (Zhang and Schneider 2010; Rai, Kumar, and Daume 2012) whose g(·) takes the form of g(Ω) = ‖Ω−1‖1 by assuming that Ω−1 is sparse.”
Efficient Output Kernel Learning for Multiple Tasks (2015, methodology): “Landmine: A data set containing binary classification problems from 19 different landmines [30].”
Learning to Multitask (2018, methodology): “The survey [34] has shown that the models proposed in [14, 13, 16, 32, 27, 33] can be formulated as problem (1) with different g ( · ) ’s, where the detailed connections between these works and problem (1) are put in the supplementary material for completeness.”
Learning Tree Structure in Multi-Task Learning (2015, unknown): “For example, low-rank structure based methods in [1, 3] can learn model parameters sharing a low dimensional subspace for multiple tasks, probabilistic MTL models [27, 25] place probabilistic priors on multiple tasks to learn the model parameters as well as identifying the task relations, regularize”