NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
This competition addresses the fundamental problem of understanding generalization in deep learning, which is crucial for making deep learning more robust and reliable for the entire deep learning community.
This paper describes a NeurIPS 2020 competition focused on predicting generalization in deep learning models. The goal was to invite the community to propose complexity measures that can accurately predict the generalization performance of these models.
Understanding generalization in deep learning is arguably one of the most important questions in deep learning. Deep learning has been successfully adopted to a large number of problems ranging from pattern recognition to complex decision making, but many recent researchers have raised many concerns about deep learning, among which the most important is generalization. Despite numerous attempts, conventional statistical learning approaches have yet been able to provide a satisfactory explanation on why deep learning works. A recent line of works aims to address the problem by trying to predict the generalization performance through complexity measures. In this competition, we invite the community to propose complexity measures that can accurately predict generalization of models. A robust and general complexity measure would potentially lead to a better understanding of deep learning's underlying mechanism and behavior of deep models on unseen data, or shed light on better generalization bounds. All these outcomes will be important for making deep learning more robust and reliable.