Metalearning with Very Few Samples Per Task

arXiv:2312.13978v2 Announce Type: replace
Abstract: Metalearning and multitask learning are two frameworks for solving a group of related learning tasks more efficiently than we could hope to solve each of the individual tasks on their own. In multitask learning, we are given a fixed set of related learning tasks and need to output one accurate model per task, whereas in metalearning we are given tasks that are drawn i.i.d. from a metadistribution and need to output some common information that …

abstract arxiv cs.ds cs.lg frameworks multitask learning per samples set solve tasks type