# Lossless Compression: A New Benchmark for Time Series Model Evaluation

arXiv: https://arxiv.org/abs/2509.21002 · HTML: https://mlsanity.com/paper/2509.21002/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2402.19072/) (2024)
- [Language Modeling Is Compression](https://mlsanity.com/paper/2309.10668/) (2023)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version](https://mlsanity.com/paper/2302.12721/) (2023)
- [A Comprehensive Survey of Deep Learning for Time Series Forecasting: Architectural Diversity and Open Challenges](https://mlsanity.com/paper/2411.05793/) (2024)
- [A Fast Transformer-based General-Purpose Lossless Compressor](https://mlsanity.com/paper/2203.16114/) (2022)
- [Time series compression: a survey](https://mlsanity.com/paper/2101.08784/) (2021)
- [DZip: improved general-purpose lossless compression based on novel neural network modeling](https://mlsanity.com/paper/1911.03572/) (2019)
- [Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation](https://mlsanity.com/paper/2405.13075/) (2024)

## Abstract (arXiv)

The evaluation of time series models has traditionally focused on four canonical tasks: forecasting, imputation, anomaly detection, and classification. While these tasks have driven significant progress, they primarily assess task-specific performance and do not rigorously measure whether a model captures the full generative distribution of the data. We introduce lossless compression as a new paradigm for evaluating time series models, grounded in Shannon's source coding theorem. This perspective establishes a direct equivalence between optimal compression length and the negative log-likelihood, providing a strict and unified information-theoretic criterion for modeling capacity. Then We define a standardized evaluation protocol and metrics. We further propose and open-source a comprehensive evaluation framework TSCom-Bench, which enables the rapid adaptation of time series models as backbones for lossless compression. Experiments across diverse datasets on state-of-the-art models, including TimeXer, iTransformer, and PatchTST, demonstrate that compression reveals distributional weaknesses overlooked by classic benchmarks. These findings position lossless compression as a principled task that complements and extends existing evaluation for time series modeling.