paper-with-me

Papers

Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation

2026-04-14 · Yilang Zhang, Abraham Jaeger Mountain, Bingcong Li, Georgios B. Giannakis arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.13263

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Optimistic Meta-Gradients

2023-01-09 · NeurIPS 2023 11

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-Learning

A History of Meta-gradient: Gradient Methods for Meta-learning

2022-02-20 · Richard S. Sutton

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-Learning

A Lazy Approach to Long-Horizon Gradient-Based Meta-Learning

2021-01-01 · ICCV 2021 10 · Muhammad Abdullah Jamal, Liqiang Wang, Boqing Gong

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-Learning

Cooperative Meta-Learning with Gradient Augmentation

2024-06-07 · Jongyun Shin, Seunjin Han, Jangho Kim

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+1

Meta-Gradients in Non-Stationary Environments

2022-09-13 · Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel 외

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…