Learning Multiple Tasks using Shared Hypotheses

By Koby Crammer, Yishay Mansour. 2012

58 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 in Deep Neural Networks (2017, background): “Finally, [Crammer and Mansour, 2012] learn a small pool of shared hypotheses and then map each task to a single hypothesis.”
A Survey on Multi-Task Learning (2017, methodology): “This approach has been extended to an iterative process in [54] in”
Diverse Few-Shot Text Classification with Multiple Metrics (2018, background): “…of similarities among single-task model parameters (Kumar and Daume III, 2012; Kang et al., 2011); or jointly assign task clusters and train model parameters for each cluster to minimize the overall training loss (Crammer and Mansour, 2012; Barzi-lai and Crammer, 2015; Murugesan et al., 2017).”
Multi-task Learning with Labeled and Unlabeled Tasks (2016, background): “For this they employ different types of transfer: instance-transfer methods re-use training samples from different tasks [13], parameter-transfer methods assume that the predictors for all tasks are similar to each other in some norm and exploit this fact through specific regularizers [16], represen”
Convex Multi-Task Learning by Clustering (2015, methodology): “We evaluated SHAMO [6] and GO-MTL [16], the former is closest in”
Robust Online Multi-Task Learning with Correlative and Personalized Structures (2017, methodology): “Most Recently, [37] proposed an algorithm, Shared Hypothesis model (SHAMO), which used a K-means-like procedure to cluster different tasks in order to learn the shared hypotheses.”
Regret Bounds for Lifelong Learning (2016, background): “A similar choice has been considered by Crammer and Mansour (2012) in the multitask setting, in which the goal is to bound the average error on a prescribed set of tasks.”
Lifelong Learning with Weighted Majority Votes (2016, background): “Note that this assumption can also be seen as a relaxation of the one used in [8].”
Adaptive Smoothed Online Multi-Task Learning (2016, methodology): “Most existing work in multi-task learning focuses on how to take advantage of these task relationships, either to share data directly [1] or to learn model parameters via cross-task regularization techniques [2, 3, 4].”
Confidence Weighted Multitask Learning (2019, methodology): “…in multitask learning focus on how to take advantage of the task relationship, either by sharing model parameters via regularization techniques (Argyriou, Evgeniou, and Pontil 2008; Zhang and Yeung 2010; Yang, Zhao, and Gao 2017) or learning cross-task data directly (Crammer and Mansour 2012).”