返回全部资讯
OpenAI 官方博客T1·基座大模型

OpenAI 提出 Reptile 元学习算法

原标题:Reptile: A scalable meta-learning algorithm
68AI 研判分

OpenAI 研究人员提出了名为 Reptile 的简单可扩展元学习算法。该算法通过重复采样任务并执行随机梯度下降,将初始参数向最终学习到的参数方向更新。Reptile 仅需黑盒访问优化器(如 SGD 或 Adam),在计算效率和性能上与一阶 MAML 相似,但实现更为简洁。

报道正文

We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the Shortest Descent algorithm to the meta-learning setting, and is mathematically similar to first-order MAML (which is a version of the well-known MAML algorithm) that only needs black-box access to an optimizer such as SGD or Adam, with similar computational efficiency and performance.