Revisiting the Robustness of the Minimum Error Entropy Criterion: A Transfer Learning Case Study
This work addresses robustness in transfer learning for real-life regression tasks, offering a simple alternative to complex methods, though it is incremental as it adapts an existing criterion.
The paper tackles the problem of distributional shifts in transfer learning by revisiting the minimum error entropy (MEE) criterion, showing that replacing mean squared error with MEE in basic algorithms achieves competitive performance with state-of-the-art methods on synthetic and real-world data.
Coping with distributional shifts is an important part of transfer learning methods in order to perform well in real-life tasks. However, most of the existing approaches in this area either focus on an ideal scenario in which the data does not contain noises or employ a complicated training paradigm or model design to deal with distributional shifts. In this paper, we revisit the robustness of the minimum error entropy (MEE) criterion, a widely used objective in statistical signal processing to deal with non-Gaussian noises, and investigate its feasibility and usefulness in real-life transfer learning regression tasks, where distributional shifts are common. Specifically, we put forward a new theoretical result showing the robustness of MEE against covariate shift. We also show that by simply replacing the mean squared error (MSE) loss with the MEE on basic transfer learning algorithms such as fine-tuning and linear probing, we can achieve competitive performance with respect to state-of-the-art transfer learning algorithms. We justify our arguments on both synthetic data and 5 real-world time-series data.