Is deeper better only when shallow is good?

Eran Malach, Shai Shalev-Shwartz

Research output: Contribution to journalConference articlepeer-review

18 Scopus citations


Understanding the power of depth in feed-forward neural networks is an ongoing challenge in the field of deep learning theory. While current works account for the importance of depth for the expressive power of neural-networks, it remains an open question whether these benefits are exploited during a gradient-based optimization process. In this work we explore the relation between expressivity properties of deep networks and the ability to train them efficiently using gradient-based algorithms. We give a depth separation argument for distributions with fractal structure, showing that they can be expressed efficiently by deep networks, but not with shallow ones. These distributions have a natural coarse-to-fine structure, and we show that the balance between the coarse and fine details has a crucial effect on whether the optimization process is likely to succeed. We prove that when the distribution is concentrated on the fine details, gradient-based algorithms are likely to fail. Using this result we prove that, at least in some distributions, the success of learning deep networks depends on whether the distribution can be approximated by shallower networks, and we conjecture that this property holds in general.

Original languageAmerican English
JournalAdvances in Neural Information Processing Systems
StatePublished - 2019
Event33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada
Duration: 8 Dec 201914 Dec 2019

Bibliographical note

Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.


Dive into the research topics of 'Is deeper better only when shallow is good?'. Together they form a unique fingerprint.

Cite this