# The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers

Source: [The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers](<https://www.sota2.com/research/paper/68fa57d21e209131ce9a8ea9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T14:58:37.618Z

Authors: Preetum Nakkiran, Behnam Neyshabur, Hanie Sedghi

Published: 2020-10-16T03:07:49.000Z

## Abstract

We propose a new framework for reasoning about generalization in deep learning. The core idea is to couple the Real World, where optimizers take stochastic gradient steps on the empirical loss, to an Ideal World, where optimizers take steps on the population loss. This leads to an alternate decomposition of test error into: (1) the Ideal World test error plus (2) the gap between the two worlds. If the gap (2) is universally small, this reduces the problem of generalization in offline learning to the problem of optimization in online learning. We then give empirical evidence that this gap between worlds can be small in realistic deep learning settings, in particular supervised image classification. For example, CNNs generalize better than MLPs on image distributions in the Real World, but this is "because" they optimize faster on the population loss in the Ideal World. This suggests our framework is a useful tool for understanding generalization in deep learning, and lays a foundation for future research in the area.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2010.08127>)

[PDF](<https://arxiv.org/pdf/2010.08127.pdf>)
