# Learned Compression of Nonlinear Time Series With Random Access

arXiv: https://arxiv.org/abs/2412.16266 · HTML: https://mlsanity.com/paper/2412.16266/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 91 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [The Case for Learned Index Structures](https://mlsanity.com/paper/1712.01208/) (2017)
- [RadixSpline: A Single-Pass Learned Index](https://mlsanity.com/paper/2004.14541/) (2020)
- [The PGM-index: a multicriteria, compressed and learned approach to data indexing](https://mlsanity.com/paper/1910.06169/) (2019)
- [Time series compression: a survey](https://mlsanity.com/paper/2101.08784/) (2021)
- [Time Series Management Systems: A Survey](https://mlsanity.com/paper/1710.01077/) (2017)
- [From Theory to Practice: Plug and Play with Succinct Data Structures](https://mlsanity.com/paper/1311.1249/) (2013)
- [Are Updatable Learned Indexes Ready?](https://mlsanity.com/paper/2207.02900/) (2022)
- [FCBench: Cross-Domain Benchmarking of Lossless Compression for Floating-Point Data](https://mlsanity.com/paper/2312.10301/) (2023)
- [On the Suitability of Neural Networks as Building Blocks for The Design of Efficient Learned Indexes](https://mlsanity.com/paper/2203.14777/) (2022)
- [Learned Monotone Minimal Perfect Hashing](https://mlsanity.com/paper/2304.11012/) (2023)
- [LeCo: Lightweight Compression via Learning Serial Correlations](https://mlsanity.com/paper/2306.15374/) (2023)
- [Standard Vs Uniform Binary Search and Their Variants in Learned Static Indexing: The Case of the Searching on Sorted Data Benchmarking Software Platform](https://mlsanity.com/paper/2201.01554/) (2022)
- [Which arithmetic operations can be performed in constant time in the RAM model with addition?](https://mlsanity.com/paper/2206.13851/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learned Static Function Data Structures](https://mlsanity.com/paper/2510.27588/) (2025)

## Abstract (arXiv)

Time series play a crucial role in many fields, including finance, healthcare, industry, and environmental monitoring. The storage and retrieval of time series can be challenging due to their unstoppable growth. In fact, these applications often sacrifice precious historical data to make room for new data. General-purpose compressors can mitigate this problem with their good compression ratios, but they lack efficient random access on compressed data, thus preventing real-time analyses. Ad-hoc streaming solutions, instead, typically optimise only for compression and decompression speed, while giving up compression effectiveness and random access functionality. Furthermore, all these methods lack awareness of certain special regularities of time series, whose trends over time can often be described by some linear and nonlinear functions. To address these issues, we introduce NeaTS, a randomly-accessible compression scheme that approximates the time series with a sequence of nonlinear functions of different kinds and shapes, carefully selected and placed by a partitioning algorithm to minimise the space. The approximation residuals are bounded, which allows storing them in little space and thus recovering the original data losslessly, or simply discarding them to obtain a lossy time series representation with maximum error guarantees. Our experiments show that NeaTS improves the compression ratio of the state-of-the-art lossy compressors that use linear or nonlinear functions (or both) by up to 14%. Compared to lossless compressors, NeaTS emerges as the only approach to date providing, simultaneously, compression ratios close to or better than the best existing compressors, a much faster decompression speed, and orders of magnitude more efficient random access, thus enabling the storage and real-time analysis of massive and ever-growing amounts of (historical) time series data.