Online Learning of Multiple Tasks with a Shared Loss

By Ofer Dekel, Philip M. Long, Yoram Singer. 2007

75 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 Artificial Intelligence

Citations in the corpus

A Survey on Multi-Task Learning (2017, methodology): “In [152], [153], under a setting where all the tasks contribute toward a common goal, the relation between tasks is measured via a global loss function and several online algorithms are proposed to use absolute norms as the global loss function.”
Adaptive Smoothed Online Multi-Task Learning (2016, methodology): “al for online multi-task learning with shared loss (OSGL) [6].”
Confidence Weighted Multitask Learning (2019, methodology): “And Dekel et al. (Dekel, Long, and Singer 2007) learned the task relationship via a global loss function.”
Provable Guarantees for Gradient-Based Meta-Learning (2019, background): “Online LTL: Learning-to-learn and multi-task learning (MTL) have both been extensively studied in the online setting, although our setting differs significantly from the one usually studied in online MTL (Abernethy et al., 2007; Dekel et al., 2007; Cavallanti et al., 2010).”
Robust Online Multi-Task Learning with Correlative and Personalized Structures (2017, background): “An earlywork [34], [35], Online Multi-Task Learning (OMTL), studied online learning of multiple tasks in parallel.”
OTL: A Framework of Online Transfer Learning (2010, background): “Finally, we note that OTL is also diﬀerent from online multi-task learning (Dekel et al., 2007), which aims to learn multiple tasks in parallel in an online learning framework.”
Online Multi-Task Learning Framework for Ensemble Forecasting (2017, methodology): “Unlike OMTLSL, ORION-ϵ enforces the constraint wt = w0 + vt, which helps to improve the performance of the ensemble forecasting task.”
Online Multi-task Learning with Hard Constraints (2009, methodology): “Multi-task learning has recently received considerable at tention, see [ DLS07 , ABR07, Men07, CCBG08].”