Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold
| dc.contributor.author | Sel, Bilgehan | en |
| dc.contributor.author | Tawaha, Ahmad | en |
| dc.contributor.author | Ding, Yuhao | en |
| dc.contributor.author | Jia, Ruoxi | en |
| dc.contributor.author | Ji, Bo | en |
| dc.contributor.author | Lavaei, Javad | en |
| dc.contributor.author | Jin, Ming | en |
| dc.date.accessioned | 2024-02-19T14:19:52Z | en |
| dc.date.available | 2024-02-19T14:19:52Z | en |
| dc.date.issued | 2023-01-01 | en |
| dc.description.abstract | Solving 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. | en |
| dc.description.version | Published version | en |
| dc.format.extent | Pages 38-50 | en |
| dc.format.mimetype | application/pdf | en |
| dc.identifier.eissn | 2640-3498 | en |
| dc.identifier.orcid | Ji, Bo [0000-0003-0149-7509] | en |
| dc.identifier.orcid | Jia, Ruoxi [0000-0001-9662-9556] | en |
| dc.identifier.orcid | Jin, Ming [0000-0001-7909-4545] | en |
| dc.identifier.uri | https://hdl.handle.net/10919/118015 | en |
| dc.identifier.volume | 211 | en |
| dc.language.iso | en | en |
| dc.rights | In Copyright | en |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | en |
| dc.title | Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold | en |
| dc.title.serial | 5th Annual Learning for Dynamics & Control Conference (L4DC 2023) | en |
| dc.type | Article - Refereed | en |
| dc.type.dcmitype | Text | en |
| dc.type.other | Article | en |
| pubs.organisational-group | /Virginia Tech | en |
| pubs.organisational-group | /Virginia Tech/Engineering | en |
| pubs.organisational-group | /Virginia Tech/Engineering/Computer Science | en |
| pubs.organisational-group | /Virginia Tech/Engineering/Electrical and Computer Engineering | en |
| pubs.organisational-group | /Virginia Tech/All T&R Faculty | en |
| pubs.organisational-group | /Virginia Tech/Engineering/COE T&R Faculty | en |