A Statistical Investigation of Long Memory in Language and Music
Alexander Greaves-Tunnell · Zaid Harchaoui

Tue Jun 11th 02:30 -- 02:35 PM @ Room 201

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.

Author Information

Alexander Greaves-Tunnell (University of Washington)
Zaid Harchaoui (University of Washington)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors