Meta-Learning with Adaptive Hyperparameters
- URL: http://arxiv.org/abs/2011.00209v2
- Date: Tue, 8 Dec 2020 06:53:01 GMT
- Title: Meta-Learning with Adaptive Hyperparameters
- Authors: Sungyong Baik, Myungsub Choi, Janghoon Choi, Heewon Kim, Kyoung Mu Lee
- Abstract summary: We focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation)
We propose a new weight update rule that greatly enhances the fast adaptation process.
- Score: 55.182841228303225
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite its popularity, several recent works question the effectiveness of
MAML when test tasks are different from training tasks, thus suggesting various
task-conditioned methodology to improve the initialization. Instead of
searching for better task-aware initialization, we focus on a complementary
factor in MAML framework, inner-loop optimization (or fast adaptation).
Consequently, we propose a new weight update rule that greatly enhances the
fast adaptation process. Specifically, we introduce a small meta-network that
can adaptively generate per-step hyperparameters: learning rate and weight
decay coefficients. The experimental results validate that the Adaptive
Learning of hyperparameters for Fast Adaptation (ALFA) is the equally important
ingredient that was often neglected in the recent few-shot learning approaches.
Surprisingly, fast adaptation from random initialization with ALFA can already
outperform MAML.
Related papers
- M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast
Self-Adaptation [145.7321032755538]
Learning to Optimize (L2O) has drawn increasing attention as it often remarkably accelerates the optimization procedure of complex tasks.
This paper investigates a potential solution to this open challenge by meta-training an L2O that can perform fast test-time self-adaptation to an out-of-distribution task.
arXiv Detail & Related papers (2023-02-28T19:23:20Z) - Faster Optimization-Based Meta-Learning Adaptation Phase [0.0]
We introduce Lambda patterns by which we restrict which weight are updated in the network during the adaptation phase.
The experiments conducted have shown that it is possible to significantly improve the MAML method in the following areas.
arXiv Detail & Related papers (2022-06-13T06:57:17Z) - Efficient Few-Shot Object Detection via Knowledge Inheritance [62.36414544915032]
Few-shot object detection (FSOD) aims at learning a generic detector that can adapt to unseen tasks with scarce training samples.
We present an efficient pretrain-transfer framework (PTF) baseline with no computational increment.
We also propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights.
arXiv Detail & Related papers (2022-03-23T06:24:31Z) - Multi-Task Meta-Learning Modification with Stochastic Approximation [0.7734726150561089]
A few-shot learning problem is one of the main benchmarks of meta-learning algorithms.
In this paper we investigate the modification of standard meta-learning pipeline that takes a multi-task approach during training.
The proposed method simultaneously utilizes information from several meta-training tasks in a common loss function.
Proper optimization of these weights can have a big influence on training of the entire model and might improve the quality on test time tasks.
arXiv Detail & Related papers (2021-10-25T18:11:49Z) - Robust MAML: Prioritization task buffer with adaptive learning process
for model-agnostic meta-learning [15.894925018423665]
Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm.
This paper proposes a more robust MAML based on an adaptive learning scheme and a prioritization task buffer.
Experimental results on meta reinforcement learning environments demonstrate a substantial performance gain.
arXiv Detail & Related papers (2021-03-15T09:34:34Z) - Meta-Learning with Neural Tangent Kernels [58.06951624702086]
We propose the first meta-learning paradigm in the Reproducing Kernel Hilbert Space (RKHS) induced by the meta-model's Neural Tangent Kernel (NTK)
Within this paradigm, we introduce two meta-learning algorithms, which no longer need a sub-optimal iterative inner-loop adaptation as in the MAML framework.
We achieve this goal by 1) replacing the adaptation with a fast-adaptive regularizer in the RKHS; and 2) solving the adaptation analytically based on the NTK theory.
arXiv Detail & Related papers (2021-02-07T20:53:23Z) - Performance-Weighed Policy Sampling for Meta-Reinforcement Learning [1.77898701462905]
Enhanced Model-Agnostic Meta-Learning (E-MAML) generates fast convergence of the policy function from a small number of training examples.
E-MAML maintains a set of policy parameters learned in the environment for previous tasks.
We apply E-MAML to developing reinforcement learning (RL)-based online fault tolerant control schemes.
arXiv Detail & Related papers (2020-12-10T23:08:38Z) - Fast Few-Shot Classification by Few-Iteration Meta-Learning [173.32497326674775]
We introduce a fast optimization-based meta-learning method for few-shot classification.
Our strategy enables important aspects of the base learner objective to be learned during meta-training.
We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach.
arXiv Detail & Related papers (2020-10-01T15:59:31Z) - Tasks, stability, architecture, and compute: Training more effective
learned optimizers, and using them to train themselves [53.37905268850274]
We introduce a new, hierarchical, neural network parameterized, hierarchical with access to additional features such as validation loss to enable automatic regularization.
Most learneds have been trained on only a single task, or a small number of tasks.
We train ours on thousands of tasks, making use of orders of magnitude more compute, resulting in generalizes that perform better to unseen tasks.
arXiv Detail & Related papers (2020-09-23T16:35:09Z) - La-MAML: Look-ahead Meta Learning for Continual Learning [14.405620521842621]
We propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory.
La-MAML achieves performance superior to other replay-based, prior-based and meta-learning based approaches for continual learning on real-world visual classification benchmarks.
arXiv Detail & Related papers (2020-07-27T23:07:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.