The matrix stick-breaking process for flexible multi-task learning

28 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.

A Survey on Multi-Task Learning (2017, methodology): “This model is extended in [59], [60] to a case where different tasks in a task cluster share useful features via a matrix stick-breaking process and a betaBernoulli hierarchical prior, respectively, and in [61] where each task is a compressive sensing task.”
Large-Scale Personalized Human Activity Recognition Using Online Multitask Learning (2013, methodology): “Huynh et al. [4] tried to discover latent activity patterns by using a Bayesian latent topic model (Bayesian LTM).”
Sparse Bayesian Multi-Task Learning (2011, methodology): “For the Yeast data set, the proposed models are significantly better than “Xue” [33], Model-1 and Model-2 [29], and the best performing model in [15].”
Variational inference in nonconjugate models (2012, unknown): “Xue et al. (2007) and Archambeau et al. (2011) treat Yeast and Scene as multi-task problems.”
Distance dependent Chinese restaurant processes (2009, unknown): “These include the dependent Dirichlet process (MacEachern, 1999) and other similar processes (Duan et al., 2007; Grifﬁn and Steel, 2006; Xue et al., 2007).”
Infinite Latent SVM for Classification and Multi-task Learning (2011, methodology): “For comparison with [23, 28], we use the overall classification accuracy, F1-Macro and F1-Micro as performance measures.”