2021/02/14 by Halil Ibrahim Gulluk, Gulluk, Halil Ibrahim, Yue Sun +5
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification
paper · pdf · doi:10.48550/arxiv.2102.07206
openalex publication_date 2021/02/14 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Constructing good representations is critical for learning complex tasks in a\nsample efficient manner. In the context of meta-learning, representations can\nbe constructed from common patterns of previously seen tasks so that a future\ntask can be learned quickly. While recent works show the benefit of\nsubspace-based representations, such results are limited to linear-regression\ntasks. This work explores a more general class of nonlinear tasks with\napplications ranging from binary classification, generalized linear models and\nneural nets. We prove that subspace-based representations can be learned in a\nsample-efficient manner and provably benefit future tasks in terms of sample\ncomplexity. Numerical results verify the theoretical predictions in\nclassification and neural-network regression tasks.\n