邻域平滑校准论文发布

1. 12:00
   arXiv · Machine Learning Theory

   邻域平滑用于校准

   论文提出把图平滑作为训练期校准的通用原则，鼓励表征空间中相邻样本具有相近的预测分布，并给出预测散度与局部置信度变化、逐点校准误差传播之间的界。作者据此设计基于图的正则项，惩罚相邻样本预测分布的 Jensen-Shannon 散度。在标准校准基准上，该方法提升预测质量，并与温度缩放等事后校准互补：在八个图像与表格设置中的七个里，温度缩放后取得所有评估训练期方法中最低 NLL。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.