BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
arXiv:2009.13357
Abstract
Meta-learning (a.k.a. learning to learn) has recently emerged as a promising paradigm for a variety of applications. There are now many meta-learning methods, each focusing on different modeling aspects of base and meta learners, but all can be (re)formulated as specific bilevel optimization problems. This work presents BOML, a modularized optimization library that unifies several meta-learning algorithms into a common bilevel optimization framework. It provides a hierarchical optimization pipeline together with a variety of iteration modules, which can be used to solve the mainstream categories of meta-learning methods, such as meta-feature-based and meta-initialization-based formulations. The library is written in Python and is available at https://github.com/dut-media-lab/BOML.
six pages
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- DARTS: Differentiable Architecture Search
- Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
- Meta-Learning with Implicit Gradients
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning
- Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
- A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton