Fast and Sample-Efficient Relevance-Based Multi-Task Representation Learning

This letter explores an approach for task-relevant multi-task representation learning when the amount of data is limited for both source tasks and target tasks. Specifically, we consider a low-dimensional setting where the goal is to sample source task data based on their relevance so as to utilize...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE control systems letters Ročník 8; s. 1397 - 1402
Hlavní autoři: Lin, Jiabin, Moothedath, Shana
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 2024
Témata:
alternating gradient descent
meta learning
Minimization
multi-task learning
Multitasking
Prediction algorithms
Representation learning
Task analysis
Training
Vectors
ISSN:2475-1456, 2475-1456
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This letter explores an approach for task-relevant multi-task representation learning when the amount of data is limited for both source tasks and target tasks. Specifically, we consider a low-dimensional setting where the goal is to sample source task data based on their relevance so as to utilize task-relevant information effectively. We present a novel learning algorithm based on an alternating projected gradient descent (GD) and minimization estimator. We present the convergence guarantee of our algorithm, excess risk, and the sample complexity of our approach. We evaluated the effectiveness of our algorithm via numerical experiments and compared it empirically against three benchmark approaches.
ISSN:2475-1456
2475-1456
DOI:10.1109/LCSYS.2024.3412880