Sel, BilgehanTawaha, AhmadDing, YuhaoJia, RuoxiJi, BoLavaei, JavadJin, Ming2024-02-192024-02-192023-01-01https://hdl.handle.net/10919/118015Solving a sequence of high-dimensional, nonconvex, but potentially similar optimization problems poses a computational challenge in engineering applications. We propose the first meta-learning framework that leverages the shared structure among sequential tasks to improve the computational efficiency and sample complexity of derivative-free optimization. Based on the observation that most practical high-dimensional functions lie on a latent low-dimensional manifold, which can be further shared among instances, our method jointly learns the meta-initialization of a search point and a meta-manifold. Theoretically, we establish the benefit of meta-learning in this challenging setting. Empirically, we demonstrate the effectiveness of the proposed algorithm in two high-dimensional reinforcement learning tasks.Pages 38-50application/pdfenIn CopyrightArticle - Refereed211Ji, Bo [0000-0003-0149-7509]Jia, Ruoxi [0000-0001-9662-9556]Jin, Ming [0000-0001-7909-4545]2640-3498