Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent
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.
Code (1)
Tasks
Few-Shot LearningMeta-LearningSimilar Papers 제목 키워드 기반
Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning
Utilizing task-invariant knowledge acquired from related tasks as prior information, meta-learning offers a principled approach to learning a new task with limited data records. Sample-efficient adaptation of this prior …
Few-Shot LearningConvergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
Although model-agnostic meta-learning (MAML) is a very successful algorithm in meta-learning practice, it can have high computational cost because it updates all model parameters over both the inner loop of task-specific…
Meta-LearningMetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption
Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power. In this paper,we propose MetaLDC, which meta-trains braininspired ultra-efficient l…
Meta-LearningFaster Optimization-Based Meta-Learning Adaptation Phase
Neural networks require a large amount of annotated data to learn. Meta-learning algorithms propose a way to decrease the number of training samples to only a few. One of the most prominent optimization-based meta-learni…
Meta-LearningLearning State-Dependent Losses for Inverse Dynamics Learning
Being able to quickly adapt to changes in dynamics is paramount in model-based control for object manipulation tasks. In order to influence fast adaptation of the inverse dynamics model's parameters, data efficiency is c…
Meta-Learning