mlsanityData to 14 Oct 2026

TinyCast: Probabilistic Zero-Shot Forecasting with Computed Periodicity

arXiv 2608.15767 ↗First posted 16 Aug 2026cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic structure of a context is worth computing rather than learning. A zero-parameter spectral detector supplies the dominant periods, the context is folded on their phase, and a dilated convolutional encoder and a block-autoregressive quantile decoder model the rest. It is smaller than every zero-shot entry on the GIFT-Eval board whose parameter count can be established. On probabilistic accuracy it defines the size-accuracy frontier. Among zero-shot entries declaring no test-data leakage it is the only one below 1.4M parameters that emits a predictive distribution, and every entry scoring better carries at least that budget. On Chronos-ZS and fev-bench every neural model ahead of it carries at least 28 times its parameters. Because the mixing path is convolutions and matrix multiplications only, it exports to static INT8 and forecasts end to end on an embedded device without per-signal fitting.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 61 references that are in the map. First posted on arXiv 16 Aug 2026.

Builds on

42 of 61 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  6. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  7. 2020GLU Variants Improve Transformercited by 1,804
  8. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  9. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  10. 2019Root Mean Square Layer Normalizationcited by 1,480
  11. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  12. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
30 more
  1. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  2. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 803
  3. 2024Chronos: Learning the Language of Time Seriescited by 759
  4. 2023A decoder-only foundation model for time-series forecastingcited by 692
  5. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  6. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
  7. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  8. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 212
  9. 2023FITS: Modeling Time Series with 10k Parameterscited by 195
  10. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  11. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 127
  12. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  13. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 120
  14. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 107
  15. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 106
  16. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 95
  17. 2025fev-bench: A Realistic Benchmark for Time Series Forecastingcited by 64
  18. 2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 60
  19. 2026Toto 2.0: Time Series Forecasting Enters the Scaling Eracited by 30
  20. 2025LightGTS: A Lightweight General Time Series Forecasting Modelcited by 29
  21. 2025Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Modelcited by 24
  22. 2025TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecastingcited by 17
  23. 2024Mamba-PTQ: Outlier Channels in Recurrent Large Language Modelscited by 15
  24. 2026Reverso: Efficient Time Series Foundation Models for Zero-shot Forecastingcited by 13
  25. 2024Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollerscited by 11
  26. 2025FlowState: Sampling-Rate-Equivariant Time-Series Forecastingcited by 8
  27. 2025Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attentioncited by 8
  28. 2026CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecastingcited by 2
  29. 2026FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontrollercited by 1
  30. 2026Don't Learn the Shape: Forecasting Periodic Time Series by Rank-1 Decompositioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameterscited by 0