Generalized Huber Loss for Robust Learning and its Efficient Minimization for a Robust Statistics
This work addresses robust statistics for machine learning practitioners, but it appears incremental as it builds upon existing Huber loss concepts.
The authors tackled the problem of robust learning by proposing a generalized Huber loss that combines properties of absolute and quadratic loss, and they developed an efficient algorithm for its minimization with comparable difficulty to traditional mean and median computations.
We propose a generalized formulation of the Huber loss. We show that with a suitable function of choice, specifically the log-exp transform; we can achieve a loss function which combines the desirable properties of both the absolute and the quadratic loss. We provide an algorithm to find the minimizer of such loss functions and show that finding a centralizing metric is not that much harder than the traditional mean and median.