Label Smoothing is a Pragmatic Information Bottleneck
By: Sota Kudo
Potential Business Impact:
Makes computer learning better by focusing on important details.
This study revisits label smoothing via a form of information bottleneck. Under the assumption of sufficient model flexibility and no conflicting labels for the same input, we theoretically and experimentally demonstrate that the model output obtained through label smoothing explores the optimal solution of the information bottleneck. Based on this, label smoothing can be interpreted as a practical approach to the information bottleneck, enabling simple implementation. As an information bottleneck method, we experimentally show that label smoothing also exhibits the property of being insensitive to factors that do not contain information about the target, or to factors that provide no additional information about it when conditioned on another variable.
Similar Papers
Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning
Machine Learning (CS)
Makes computer learning ignore bad labels.
Calibrated Language Models and How to Find Them with Label Smoothing
Machine Learning (CS)
Makes AI smarter and more honest.
A Generalized Information Bottleneck Theory of Deep Learning
Machine Learning (CS)
Helps computers learn better by understanding feature connections.