论文标题
体重向量的低损失连接：基于分布的方法
Low-loss connection of weight vectors: distribution-based approaches
论文作者
论文摘要
最近的研究表明，过度参数化网络的损耗表面集合完全或大致连接。我们在实验中描述和比较了一系列用于通过该表面上低损耗曲线连接两个低损坏点的方法。我们的方法的准确性和复杂性各不相同。我们的大多数方法基于“宏观”分布假设，有些方法对要连接的点的详细属性不敏感。某些方法需要先前对“全局连接模型”进行培训，然后可以将其应用于任何一对。该方法的准确性通常与其对端点细节的复杂性和敏感性相关。
Recent research shows that sublevel sets of the loss surfaces of overparameterized networks are connected, exactly or approximately. We describe and compare experimentally a panel of methods used to connect two low-loss points by a low-loss curve on this surface. Our methods vary in accuracy and complexity. Most of our methods are based on "macroscopic" distributional assumptions, and some are insensitive to the detailed properties of the points to be connected. Some methods require a prior training of a "global connection model" which can then be applied to any pair of points. The accuracy of the method generally correlates with its complexity and sensitivity to the endpoint detail.
