NeurIPS 2020 Competition: Predicting Generalization in Deep Learning

TL;DR

This paper discusses a NeurIPS 2020 competition focused on developing complexity measures to predict the generalization performance of deep learning models, aiming to enhance understanding and reliability.

Contribution

It introduces a community challenge to identify effective complexity measures for predicting deep learning generalization, encouraging progress in theoretical understanding.

Findings

Community proposed various complexity measures

Some measures showed promising correlation with generalization

Results highlight the difficulty of accurately predicting generalization

Abstract

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.