记住在使用深度学习进行回归时要纠正偏差!
Remember to correct the bias when using deep learning for regression!
摘要:
当训练深度学习模型进行最小二乘回归时,我们不能期望在固定训练时间后或基于保持数据集的性能选择的最终模型的训练误差残差总和为零。如果我们对许多数据点上的总聚合性能感兴趣,这可能会引入累积的系统误差。我们建议在训练后调整机器学习模型的偏差作为默认的后处理步骤,这有效地解决了这个问题。在示例性实验中证明了误差累积的精确性和偏差校正的有效性。
英文摘要:
When training deep learning models for least-squares regression, we cannot expect that the training error residuals of the final model, selected after a fixed training time or based on performance on a hold-out data set, sum to zero. This can introduce a systematic error that accumulates if we are interested in the total aggregated performance over many data points. We suggest to adjust the bias of the machine learning model after training as a default postprocessing step, which efficiently solves the problem. The severeness of the error accumulation and the effectiveness of the bias correction is demonstrated in exemplary experiments.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。