Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.13486 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912597362606080 |
|---|---|
| author | Zhang, Yilang Li, Bingcong Giannakis, Georgios B. |
| author_facet | Zhang, Yilang Li, Bingcong Giannakis, Georgios B. |
| contents | Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited. A fundamental challenge in meta-learning is how to quickly "adapt" the extracted prior in order to train a task-specific model within a few optimization steps. Existing approaches deal with this challenge using a preconditioner that enhances convergence of the per-task training process. Though effective in representing locally a quadratic training loss, these simple linear preconditioners can hardly capture complex loss geometries. The present contribution addresses this limitation by learning a nonlinear mirror map, which induces a versatile distance metric to enable capturing and optimizing a wide range of loss geometries, hence facilitating the per-task training. Numerical tests on few-shot learning datasets demonstrate the superior expressiveness and convergence of the advocated approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_13486 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent Zhang, Yilang Li, Bingcong Giannakis, Georgios B. Machine Learning Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited. A fundamental challenge in meta-learning is how to quickly "adapt" the extracted prior in order to train a task-specific model within a few optimization steps. Existing approaches deal with this challenge using a preconditioner that enhances convergence of the per-task training process. Though effective in representing locally a quadratic training loss, these simple linear preconditioners can hardly capture complex loss geometries. The present contribution addresses this limitation by learning a nonlinear mirror map, which induces a versatile distance metric to enable capturing and optimizing a wide range of loss geometries, hence facilitating the per-task training. Numerical tests on few-shot learning datasets demonstrate the superior expressiveness and convergence of the advocated approach. |
| title | Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2312.13486 |