Skip to main navigation Skip to search Skip to main content

Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration

  • Yan Sun
  • , Wenjun Xiong
  • , Faming Liang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep learning has powered recent successes of artificial intelligence (AI). However, the deep neural network, as the basic model of deep learning, has suffered from issues such as local traps and miscalibration. In this paper, we provide a new framework for sparse deep learning, which has the above issues addressed in a coherent way. In particular, we lay down a theoretical foundation for sparse deep learning and propose prior annealing algorithms for learning sparse neural networks. The former has successfully tamed the sparse deep neural network into the framework of statistical modeling, enabling prediction uncertainty correctly quantified. The latter can be asymptotically guaranteed to converge to the global optimum, enabling the validity of the down-stream statistical inference. Numerical result indicates the superiority of the proposed method compared to the existing ones.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
EditorsMarc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
PublisherNeural information processing systems foundation
Pages22301-22312
Number of pages12
ISBN (Electronic)9781713845393
StatePublished - 2021
Externally publishedYes
Event35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online
Duration: Dec 6 2021Dec 14 2021

Publication series

NameAdvances in Neural Information Processing Systems
Volume27
ISSN (Print)1049-5258

Conference

Conference35th Conference on Neural Information Processing Systems, NeurIPS 2021
CityVirtual, Online
Period12/6/2112/14/21

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Computer Networks and Communications

Keywords

  • Asymptotic Normality
  • Posterior Consistency
  • Prior Annealing
  • Structure Selection
  • Uncertainty Quantification

Fingerprint

Dive into the research topics of 'Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration'. Together they form a unique fingerprint.

Cite this