Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation
Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks, even with limited data records. Gradient-based meta-learning (GBML) relies on gradient descent (GD) to adapt the prior to a new task. Albeit effective, these methods incur high computational overhead that scales linearly with the number of GD steps. To enhance efficiency and scalability, existing methods approximate the gradient of prior parameters (meta-gradient) via truncated backpropagation, yet suffer large approximation errors. Targeting accurate approximation, this work puts forth binomial GBML (BinomGBML), which relies on a truncated binomial expansion for meta-gradient estimation. This novel expansion endows more information in the meta-gradient estimation via efficient parallel computation. As a running paradigm applied to model-agnostic meta-learning (MAML), the resultant BinomMAML provably enjoys error bounds that not only improve upon existing approaches, but also decay super-exponentially under mild conditions. Numerical tests corroborate the theoretical analysis and showcase boosted performance with slightly increased computational overhead.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Optimistic Meta-Gradients
We study the connection between gradient-based meta-learning and convex op-timisation. We observe that gradient descent with momentum is a special case of meta-gradients, and building on recent results in optimisation, w…
Meta-LearningA History of Meta-gradient: Gradient Methods for Meta-learning
The history of meta-learning methods based on gradient descent is reviewed, focusing primarily on methods that adapt step-size (learning rate) meta-parameters.
Meta-LearningA Lazy Approach to Long-Horizon Gradient-Based Meta-Learning
Gradient-based meta-learning relates task-specific models to a meta-model by gradients. By this design, an algorithm first optimizes the task-specific models by an inner loop and then backpropagates meta-gradients throug…
Few-Shot LearningMeta-LearningCooperative Meta-Learning with Gradient Augmentation
Model agnostic meta-learning (MAML) is one of the most widely used gradient-based meta-learning, consisting of two optimization loops: an inner loop and outer loop. MAML learns the new task from meta-initialization param…
Few-Shot Image Classificationimage-classificationImage ClassificationMeta-Learning+1Meta-Gradients in Non-Stationary Environments
Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties…