# A Statistical Investigation of Long Memory in Language and Music

arXiv: https://arxiv.org/abs/1904.03834 · HTML: https://mlsanity.com/paper/1904.03834/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 8 of 8)

- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [Liquid Structural State-Space Models](https://mlsanity.com/paper/2209.12951/) (2022)
- [Temporal Consistency Learning of inter-frames for Video Super-Resolution](https://mlsanity.com/paper/2211.01639/) (2022)
- [On the Memory Mechanism of Tensor-Power Recurrent Models](https://mlsanity.com/paper/2103.01521/) (2021)
- [Fractional dynamics foster deep learning of COPD stage prediction](https://mlsanity.com/paper/2303.07537/) (2023)
- [ARISE: ApeRIodic SEmi-parametric Process for Efficient Markets without Periodogram and Gaussianity Assumptions](https://mlsanity.com/paper/2111.06222/) (2021)
- [Making Every Frame Matter: Continuous Activity Recognition in Streaming Video via Adaptive Video Context Modeling](https://mlsanity.com/paper/2410.14993/) (2024)
- [Valid and Efficient Split Conformal Regression for Time Series](https://mlsanity.com/paper/2609.33866/) (2026)

## Abstract (arXiv)

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.