Skip to content
Hot eventLive

用保形机器学习验证企业排放并量化绿漂

1 reports1 sources17 hr ago updated

Get the story

AI overview

2026年10月5日,arXiv 发表《漂绿的代价:用 Conformal 机器学习进行算法验证与市场约束》研究。该研究将美国 SEC 财务基本面与 EPA 设施级温室气体登记数据融合,建立物理企业排放的数学保证基线,并采用梯度提升架构与 Mondrian Conformal Prediction 构建 Conformal-Weighted Continuous Divergence(CWCD)指标,用于算法验证与市场约束。

Generated from reports · updated 17 hr ago

Timeline

Follow the coverage from different angles.

Oct 5, 2026
  1. arXiv · Machine Learning Theory
    漂绿的代价:用 Conformal 机器学习进行算法验证与市场约束

    研究将美国 SEC 财务基本面与 EPA 设施级温室气体登记数据融合,建立物理企业排放的数学保证基线,并用梯度提升架构与 Mondrian Conformal Prediction 构建 Conformal-Weighted Continuous Divergence(CWCD)指标。

Heat trend

Current heat 6·Comparable peak 10(Oct 5)·Comparable change over 24 hours –

02.557.510Oct5Oct5Oct6Oct6

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.