paper-with-me

홈 › Papers

Meta-Learning with Versatile Loss Geometries for Fast Adaptation Using Mirror Descent

2023-12-20 · Yilang Zhang, Bingcong Li, Georgios B. Giannakis

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.

📄 PDF Abstract BibTeX arXiv:2312.13486

Code (1)

zhangyilang/metamirrordescent 공식 구현 pytorch

Tasks

Few-Shot LearningMeta-Learning

Similar Papers 제목 키워드 기반

Learnable Loss Geometries with Mirror Descent for Scalable and Convergent Meta-Learning

2025-09-02 · Yilang Zhang, Bingcong Li, Georgios B. Giannakis arxiv

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 Learning

Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters

2020-06-16 · NeurIPS 2020 12 · Kaiyi Ji, Jason D. Lee, Yingbin Liang, H. Vincent Poor

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-Learning

MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption

2023-02-23 · Yejia Liu, Shijin Duan, Xiaolin Xu, Shaolei Ren

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-Learning

Faster Optimization-Based Meta-Learning Adaptation Phase

2022-06-13 · Kostiantyn Khabarlak

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-Learning

Learning State-Dependent Losses for Inverse Dynamics Learning

2020-03-10 · Kristen Morse, Neha Das, Yixin Lin, Austin S. Wang 외

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