ICML 2019oral33 citations

A Statistical Investigation of Long Memory in Language and Music

Alexander Greaves-Tunnell, Zaid Harchaoui

Abstract

Representation and learning of long-range dependencies is a central challenge confronted in modern applications of machine learning to sequence data. Yet despite the prominence of this issue, the basic problem of measuring long-range dependence, either in a given data source or as represented in a trained deep model, remains largely limited to heuristic tools. We contribute a statistical framework for investigating long-range dependence in current applications of deep sequence modeling, drawing on the well-developed theory of long memory stochastic processes. This framework yields testable implications concerning the relationship between long memory in real-world data and its learned representation in a deep learning architecture, which are explored through a semiparametric framework adapted to the high-dimensional setting.

BibTeX
@InProceedings{pmlr-v97-greaves-tunnell19a,
  title = 	 {A Statistical Investigation of Long Memory in Language and Music},
  author =       {Greaves-Tunnell, Alexander and Harchaoui, Zaid},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2394--2403},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/greaves-tunnell19a/greaves-tunnell19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/greaves-tunnell19a.html},
  abstract = 	 {Representation and learning of long-range dependencies is a central challenge confronted in modern applications of machine learning to sequence data. Yet despite the prominence of this issue, the basic problem of measuring long-range dependence, either in a given data source or as represented in a trained deep model, remains largely limited to heuristic tools. We contribute a statistical framework for investigating long-range dependence in current applications of deep sequence modeling, drawing on the well-developed theory of long memory stochastic processes. This framework yields testable implications concerning the relationship between long memory in real-world data and its learned representation in a deep learning architecture, which are explored through a semiparametric framework adapted to the high-dimensional setting.}
}