Multitask learning is a powerful framework that enables one to simultaneously learn multiple related tasks by sharing information between them. Quantifying uncertainty in the estimated tasks is of pivotal importance for many downstream applications, such as online or active learning. In this work, we provide novel confidence intervals for multitask regression in the challenging agnostic setting, i.e., when neither the similarity between tasks nor the tasks’ features are available to the learner. The obtained intervals do not require i.i.d. data and can be directly applied to bound the regret in online learning. Through a refined analysis of the multitask information gain, we obtain new regret guarantees that, depending on a task similarity parameter, can significantly improve over treating tasks independently. We further propose a novel online learning algorithm that achieves such improved regret without knowing this parameter in advance, i.e., automatically adapting to task similarity. As a second key application of our results, we introduce a novel multitask active learning setup where several tasks must be simultaneously optimized, but only one of them can be queried for feedback by the learner at each round. For this problem, we design a no-regret algorithm that uses our confidence intervals to decide which task should be queried. Finally, we empirically validate our bounds and algorithms on synthetic and real-world (drug discovery) data.

Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning / P. Giuseppe Sessa, P. Laforgue, N. Cesa Bianchi, A. Krause (ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS). - In: Advances in Neural Information Processing Systems 36 / [a cura di] A. Oh, T. Neumann, A. Globerson, K. Saenko, M. Hardt, S. Levine. - [s.l] : Curran Associates, 2023. - pp. 6770-6781 (( Intervento presentato al 37. convegno Neural Information Processing Systems nel 2023.

Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning

P. Laforgue
Secondo
;
N. Cesa Bianchi
Penultimo
;
2023

Abstract

Multitask learning is a powerful framework that enables one to simultaneously learn multiple related tasks by sharing information between them. Quantifying uncertainty in the estimated tasks is of pivotal importance for many downstream applications, such as online or active learning. In this work, we provide novel confidence intervals for multitask regression in the challenging agnostic setting, i.e., when neither the similarity between tasks nor the tasks’ features are available to the learner. The obtained intervals do not require i.i.d. data and can be directly applied to bound the regret in online learning. Through a refined analysis of the multitask information gain, we obtain new regret guarantees that, depending on a task similarity parameter, can significantly improve over treating tasks independently. We further propose a novel online learning algorithm that achieves such improved regret without knowing this parameter in advance, i.e., automatically adapting to task similarity. As a second key application of our results, we introduce a novel multitask active learning setup where several tasks must be simultaneously optimized, but only one of them can be queried for feedback by the learner at each round. For this problem, we design a no-regret algorithm that uses our confidence intervals to decide which task should be queried. Finally, we empirically validate our bounds and algorithms on synthetic and real-world (drug discovery) data.
Settore INF/01 - Informatica
   European Lighthouse on Secure and Safe AI (ELSA)
   ELSA
   EUROPEAN COMMISSION
   101070617

   Learning in Markets and Society
   MINISTERO DELL'UNIVERSITA' E DELLA RICERCA
   2022EKNE5K_001

   European Lighthouse of AI for Sustainability (ELIAS)
   ELIAS
   EUROPEAN COMMISSION
   101120237
2023
https://papers.nips.cc/paper_files/paper/2023/file/15d15045f93b44d933a260b249608d43-Supplemental-Conference.pdf
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
NeurIPS-2023-multitask-learning-with-no-regret-from-improved-confidence-bounds-to-active-learning-Paper-Conference.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 1.4 MB
Formato Adobe PDF
1.4 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/1034111
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact