The benefit of multitask representation learning

MaRDI QIDQ2810898zbMATH OpenFDO

Authors Andreas Maurer, Massimiliano Pontil, Bernardino Romera-Paredes

Publication date 6 June 2016

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1505.06279, http://jmlr.csail.mit.edu/papers/v17/15-242.html

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Multiplicative multitask feature learning
• Multi-stage multi-task feature learning
• Learning Theory and Kernel Machines
• Convex multi-task feature learning

Cited in

(30)

• A notion of task relatedness yielding provable multiple-task learning guarantees
• Adaptive transfer learning
• A no-free-lunch theorem for multitask learning
• Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach
• Multiplicative multitask feature learning
• A Vector-Contraction Inequality for Rademacher Complexities
• Learning sparsely used overcomplete dictionaries via alternating minimization
• A robust learning approach for regression models based on distributionally robust optimization
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Factorisable multitask quantile regression
• Domain generalization by marginal transfer learning
• Learning Theory and Kernel Machines
• Dimensionality-dependent generalization bounds for \(k\)-dimensional coding schemes
• Multi-asset closed-loop reservoir management using deep reinforcement learning
• A penalized complexity prior for deep Bayesian transfer learning with application to materials informatics
• Adaptive and robust multi-task learning
• Best-effort adaptation
• Joint learning of linear time-invariant dynamical systems
• Deep networks for system identification: a survey
• Learning from similar linear representations: adaptivity, minimaxity, and robustness
• Meta representation learning with contextual linear bandits
• Hyperparameter optimization in machine learning
• Nonlinear meta-learning can guarantee faster rates
• Robust transfer learning with unreliable source data
• Integrative tensor regression for stratified data with application to neuroimaging analysis
• Supervised learning with evolving tasks and performance guarantees
• Bayes meets Bernstein at the meta level: an analysis of fast rates in meta-learning with PAC-Bayes
• Semi-supervised group DRO: combating sparsity with unlabeled data
• Generalize across tasks: efficient algorithms for linear representation learning
• Few-shot multi-task learning of linear invariant features with meta subspace pursuit

This page was built for publication: The benefit of multitask representation learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2810898)