mlsanityData to 14 Oct 2026

NanoForecast v0.5: Competitive Time Series Forecasting Through Training Pipeline Optimization

arXiv 2609.31669 ↗First posted 15 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present NanoForecast v0.5, a 6.5M-parameter forecaster that competes with models 31x its size (TimesFM, 200M parameters) after training pipeline fixes and no architecture change. Retraining the v0.3 architecture with corrected loss-scope handling, tensor shape alignment, and wider augmentation coverage cuts overall Mean Absolute Scaled Error by 43.8% under one fixed protocol (MASE 3.030 to 1.704) on the same data and compute budget. NanoForecast v0.5 beats TimesFM on all three ETT datasets (MASE 0.676/1.110/0.287 vs. 0.705/1.360/0.545) and on exchange rate (4.317 vs. 4.383); TimesFM keeps a clear lead on the high-cardinality electricity and traffic sets. Against PatchTST (15M+ parameters, official configuration), v0.5 wins all three ETT sets. Training takes about 12 hours on a single cloud GPU (NVIDIA T4, Google Colab) and inference needs no GPU (measurements in this paper are on an Apple M4 CPU). We release all code, pretrained checkpoints, and evaluation framework under Apache 2.0 at https://github.com/eulogik/NanoForecast

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 15 Sep 2026.

Builds on

17 of 24 references.

References · 17

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  3. 2020GLU Variants Improve Transformercited by 1,804
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  5. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  7. 2024Chronos: Learning the Language of Time Seriescited by 759
  8. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  9. 2023A decoder-only foundation model for time-series forecastingcited by 692
  10. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  11. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
  12. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
5 more
  1. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
  2. 2023Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecastingcited by 113
  3. 2024SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attentioncited by 44
  4. 2026Reverso: Efficient Time Series Foundation Models for Zero-shot Forecastingcited by 13
  5. 2023FrAug: Frequency Domain Augmentation for Time Series Forecastingcited by 8

Built on by

Not cited yet.