Pith. sign in

REVIEW 9 cited by

FITS: Modeling Time Series with $10k$ Parameters

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2307.03756 v3 pith:DDAUHVGG submitted 2023-07-06 cs.LG

classification cs.LG
keywords fitsseriestimedatalightweightmodelmodelsparameters
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis. Unlike existing models that directly process raw time-domain data, FITS operates on the principle that time series can be manipulated through interpolation in the complex frequency domain. By discarding high-frequency components with negligible impact on time series data, FITS achieves performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks, while having a remarkably compact size of only approximately $10k$ parameters. Such a lightweight model can be easily trained and deployed in edge devices, creating opportunities for various applications. The code is available in: \url{https://github.com/VEWOXIC/FITS}

Discussion (0). Sign in to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection

    cs.LG 2026-03 conditional novelty 6.0 of 10

    Predicting multi-head attention queries from history and scoring cosine mismatch against an EMA target, combined with reconstruction error, improves unsupervised multivariate anomaly ranking and localization.

  2. Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting

    cs.LG 2026-02 conditional novelty 6.0 of 10

    TimeGS forecasts time series by rasterizing learned Gaussian kernels on a period-phase grid, but its state-of-the-art claim is contradicted by its own benchmark table.

  3. Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Services

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Fremer forecasts cloud workloads by aligning frequency spectra via linear padding, filtering noise, and attending over frequency combinations.

  4. When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A2P trains a shared transformer to forecast future time series and detect anomalies in the forecasted signal, using synthetic anomaly prompts, and reports higher F1 than forecasting-plus-detection baselines on four datasets.

  5. LightGTS: A Lightweight General Time Series Forecasting Model

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A lightweight time series foundation model using period-aligned patches and parallel decoding reports zero-shot and full-shot accuracy on nine benchmarks comparable to much larger models.

  6. A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting

    cs.LG 2025-06 conditional novelty 6.0 of 10

    DST-SGNN uses a Stiefel-manifold-constrained graph Fourier transform and a dynamic graph optimizer to achieve efficient and accurate spatio-temporal forecasting.

  7. Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Using Fourier basis expansion to build time-frequency features improves long-term and short-term time series forecasting across linear, MLP, and transformer backbones.

  8. Enhancing deep learning models for time series classification via knowledge distillation

    cs.LG 2026-07 conditional novelty 4.0 of 10

    Knowledge distillation most benefits intermediate-complexity students for time series classification, cutting parameters sharply while matching teacher accuracy across FCN, Inception, and ConvTran on UCR.

  9. MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models

    cs.LG 2025-07 conditional novelty 4.0 of 10

    MoFE-Time reports average MSE 0.2755 and MAE 0.3226 across six public benchmarks, about 7% lower than Time-MoE, by adding frequency-domain experts to a Mixture of Experts transformer.

Pith tools