arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.00093cs.NEcs.AIcs.LG
收藏

基于TPU的元学习分布式演化策略

Distributed Evolution Strategies Using TPUs for Meta-Learning

New York University(纽约大学);The Woodlands College Park High School(伍德兰兹大学公园高中)

Alex Sheng, Derek He

摘要:

元学习传统上依赖于整个任务的反向传播,以迭代地改善模型的学习动态。然而,当扩展到复杂任务时,这种方法在计算上是难以处理的。我们提出了一种分布式进化元学习策略,使用张量处理单元(TPU),是高度并行和可扩展的任意长的任务,而不会增加内存成本。使用在Omniglot数据集上使用演化策略训练的原型网络,我们在5次分类问题上实现了98.4%的准确率。我们的算法使用的内存比自动微分少40倍来计算梯度,所得模型的准确度在反向传播训练等效模型(99.6%)的1.3%以内。我们观察到更好的分类准确率高达99.1%,更大的人口配置。我们进一步通过实验验证了ES-ProtoNet在各种训练条件下的稳定性和性能(不同的群体大小,模型大小,工人数量,镜头,方式,ES超参数等)。我们的贡献是双重的:我们提供了第一个评估的进化元学习在监督设置,并创建一个通用的框架分布式演化策略TPU。

英文摘要:

Meta-learning traditionally relies on backpropagation through entire tasks to iteratively improve a model's learning dynamics. However, this approach is computationally intractable when scaled to complex tasks. We propose a distributed evolutionary meta-learning strategy using Tensor Processing Units (TPUs) that is highly parallel and scalable to arbitrarily long tasks with no increase in memory cost. Using a Prototypical Network trained with evolution strategies on the Omniglot dataset, we achieved an accuracy of 98.4% on a 5-shot classification problem. Our algorithm used as much as 40 times less memory than automatic differentiation to compute the gradient, with the resulting model achieving accuracy within 1.3% of a backpropagation-trained equivalent (99.6%). We observed better classification accuracy as high as 99.1% with larger population configurations. We further experimentally validate the stability and performance of ES-ProtoNet across a variety of training conditions (varying population size, model size, number of workers, shot, way, ES hyperparameters, etc.). Our contributions are twofold: we provide the first assessment of evolutionary meta-learning in a supervised setting, and create a general framework for distributed evolution strategies on TPUs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑