Chiyuan Zhang, Moritz Hardt, Oriol Vinyals, Samy Bengio, Benjamin Recht
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the model family, or to the regularization techniques used during training. Through extensive systematic experiments, we show how these traditional approaches fail to explain why large neural networks generalize well in practice. Specifically, our experiments establish that state-of-the-art convolutional networks for image classification trained with stochastic gradient methods easily fit a random labeling of the training data. This phenomenon is qualitatively unaffected by explicit regularization, and occurs even if we replace the true images by completely unstructured random noise. We corroborate these experimental findings with a theoretical construction showing that simple depth two neural networks already have perfect finite sample expressivity as soon as the number of parameters exceeds the number of data points as it usually does in practice. We interpret our experimental findings by comparison with traditional models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1611.03530")
get_code_for_paper("1611.03530")
have("1611.03530")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1611.03530.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1611.03530)
Connect an agent — have() is free.