Search Results for author:
Found 5 papers, 1 papers with code
IW-GAE: Importance weighted group accuracy estimation for improved calibration and model selection in unsupervised domain adaptation
Extensive experiments show the effectiveness of group accuracy estimation on model calibration and model selection.
Revisiting Explicit Regularization in Neural Networks for Reliable Predictive Probability
In this work, we revisit the role and importance of explicit regularization methods for generalization of the predictive probability, not just the generalization of the 0-1 loss.
Revisiting Explicit Regularization in Neural Networks for Well-Calibrated Predictive Uncertainty
From the statistical learning perspective, complexity control via explicit regularization is a necessity for improving the generalization of over-parameterized models.
Being Bayesian about Categorical Probability
Neural networks utilize the softmax as a building block in classification tasks, which contains an overconfidence problem and lacks an uncertainty representation ability.
Regularizing activations in neural networks via distribution matching with the Wasserstein metric
We propose the projected error function regularization loss (PER) that encourages activations to follow the standard normal distribution.
