Meta-Learning with Generalized Ridge Regression: High-dimensional Asymptotics, Optimality and Hyper-covariance Estimation

arXiv:2403.19720v1 Announce Type: cross
Abstract: Meta-learning involves training models on a variety of training tasks in a way that enables them to generalize well on new, unseen test tasks. In this work, we consider meta-learning within the framework of high-dimensional multivariate random-effects linear models and study generalized ridge-regression based predictions. The statistical intuition of using generalized ridge regression in this setting is that the covariance structure of the random regression coefficients could be leveraged to make better predictions on new …

abstract arxiv covariance cs.lg effects framework generalized linear math.st meta meta-learning multivariate random random-effects regression ridge ridge-regression stat.ml stat.th study tasks test them training training models type work