Huber Loss 及 tensorflow实现

    Huber Loss 相当于平方误差的推广，通过设置delta的值，使损失函数鲁棒性更强，从而减弱离群点（outliers）对模型的影响。当delta为无穷大时，Huber Loss 退化为Squared Loss.

tensorflow实现如下：

def huber_loss(labels, predictions, delta=1.0):
    residual = tf.abs(predictions - labels)
    condition = tf.less(residual, delta)
    small_res = 0.5 * tf.square(residual)
    large_res = delta * residual - 0.5 * tf.square(delta)
    return tf.select(condition, small_res, large_res)

参考：Stanford CS20SI tensorflow