论文标题
可识别性，公制空间中的KL属性和亚级别曲线
Identifiability, the KL property in metric spaces, and subgradient curves
论文作者
论文摘要
可识别性以及部分平滑度密切相关的概念，统一经典的活动设置方法和更一般的解决方案结构概念。各种优化算法在离散时间内生成迭代，最终仅限于可识别集。我们提出了有关可识别性的两个新观点。第一个将概念提炼为简单的度量属性，不仅适用于欧几里得的设置，还适用于对歧管及以后的优化；第二个揭示了亚级别下降曲线的类似连续时间行为。 Kurdya-lojasiewicz属性通常在离散时间和连续时间控制融合：我们探索其与可识别性的相互作用。
Identifiability, and the closely related idea of partial smoothness, unify classical active set methods and more general notions of solution structure. Diverse optimization algorithms generate iterates in discrete time that are eventually confined to identifiable sets. We present two fresh perspectives on identifiability. The first distills the notion to a simple metric property, applicable not just in Euclidean settings but to optimization over manifolds and beyond; the second reveals analogous continuous-time behavior for subgradient descent curves. The Kurdya-Lojasiewicz property typically governs convergence in both discrete and continuous time: we explore its interplay with identifiability.
