线性递归特征机动力学与有限样本轨迹恢复研究

1. 12:00
   arXiv · Machine Learning Theory

   线性递归特征机的精确动力学与有限样本轨迹恢复

   论文研究线性递归特征机（RFM）在带噪多输出回归中的动力学与统计性质，输入为各向同性次高斯数据，目标由维度为 d 的低秩教师矩阵生成。作者将线性 RFM 与迭代重加权最小二乘的已知联系从插值情形扩展到带噪岭正则化多输出回归，并证明学习到的特征矩阵在每轮迭代都接近其无限数据理想对应。

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.