Online learning of multiple tasks with a shared loss

Ofer Dekel, Philip M. Long, Yoram Singer

Research output: Contribution to journalArticlepeer-review

35 Scopus citations


We study the problem of learning multiple tasks in parallel within the online learning framework. On each online round, the algorithm receives an instance for each of the parallel tasks and responds by predicting the label of each instance. We consider the case where the predictions made on each round all contribute toward a common goal. The relationship between the various tasks is defined by a global loss function, which evaluates the overall quality of the multiple predictions made on each round. Specifically, each individual prediction is associated with its own loss value, and then these multiple loss values are combined into a single number using the global loss function. We focus on the case where the global loss function belongs to the family of absolute norms, and present several online learning algorithms for the induced problem. We prove worst-case relative loss bounds for all of our algorithms, and demonstrate the effectiveness of our approach on a large-scale multiclass-multilabel text categorization problem.

Original languageEnglish (US)
Pages (from-to)2233-2264
Number of pages32
JournalJournal of Machine Learning Research
StatePublished - Oct 2007

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Statistics and Probability


  • Multiclass multilabel classiifcation
  • Multitask learning
  • Online learning
  • Perceptron


Dive into the research topics of 'Online learning of multiple tasks with a shared loss'. Together they form a unique fingerprint.

Cite this