Timezone: »

 
Spotlight
Provable Meta-Learning of Linear Representations
Nilesh Tripuraneni · Chi Jin · Michael Jordan

Wed Jul 21 06:30 PM -- 06:35 PM (PDT) @
in Learning Theory 11 »

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning---a key tool for performing meta-learning---learns a data representation that can transfer knowledge across multiple tasks, which is essential in regimes where data is scarce. Despite a recent surge of interest in the practice of meta-learning, the theoretical underpinnings of meta-learning algorithms are lacking, especially in the context of learning transferable representations. In this paper, we focus on the problem of multi-task linear regression---in which multiple linear regression models share a common, low-dimensional linear representation. Here, we provide provably fast, sample-efficient algorithms to address the dual challenges of (1) learning a common set of features from multiple, related tasks, and (2) transferring this knowledge to new, unseen tasks. Both are central to the general problem of meta-learning. Finally, we complement these results by providing information-theoretic lower bounds on the sample complexity of learning these linear features.

Keywords: Statistical Learning Theory

Author Information

Nilesh Tripuraneni (UC Berkeley)
Chi Jin (Princeton University)
Michael Jordan (UC Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors