论文标题
实施更好的条件元学习以进行快速射击适应
On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation
论文作者
论文摘要
受到预处理概念的启发，我们提出了一种新的方法，以提高基于梯度的元学习方法的适应速度，而不会产生额外的参数。我们证明，将优化问题重新塑造到非线性最小二乘公式的公式提供了一种原则性的方法，可以根据条件数量和本地曲率的概念来主动执行元模型的$ \ textit {witchitioned} $参数空间。我们的全面评估表明，所提出的方法明显优于其不受约束的对应物，尤其是在初始适应步骤中，同时在几个几次分类任务上取得了可比或更好的总体结果 - 创造了动态选择推理时间的适应性步骤的数量。
Inspired by the concept of preconditioning, we propose a novel method to increase adaptation speed for gradient-based meta-learning methods without incurring extra parameters. We demonstrate that recasting the optimization problem to a non-linear least-squares formulation provides a principled way to actively enforce a $\textit{well-conditioned}$ parameter space for meta-learning models based on the concepts of the condition number and local curvature. Our comprehensive evaluations show that the proposed method significantly outperforms its unconstrained counterpart especially during initial adaptation steps, while achieving comparable or better overall results on several few-shot classification tasks -- creating the possibility of dynamically choosing the number of adaptation steps at inference time.
