Paper ID: 2308.02293
Outlier-Robust Neural Network Training: Efficient Optimization of Transformed Trimmed Loss with Variation Regularization
Akifumi Okuno, Shotaro Yagishita
In this study, we consider outlier-robust predictive modeling using highly-expressive neural networks. To this end, we employ (1) a transformed trimmed loss (TTL), which is a computationally feasible variant of the classical trimmed loss, and (2) a higher-order variation regularization (HOVR) of the prediction model. Note that using only TTL to train the neural network may possess outlier vulnerability, as its high expressive power causes it to overfit even the outliers perfectly. However, simultaneously introducing HOVR constrains the effective degrees of freedom, thereby avoiding fitting outliers. We newly provide an efficient stochastic algorithm for optimization and its theoretical convergence guarantee. (*Two authors contributed equally to this work.)
Submitted: Aug 4, 2023