- Rating
- 3(+1)
- Confidence
- 3(−1)
- Informativeness
- 2(+1)
- Presentation
- 2(+1)
- Soundness
- 2
Read review
Paper summary
This paper proposes TinyCycle, a highly parameter-efficient time-series forecasting method that uses closed-form fitting to exploit recurring periodic patterns without gradient-based training. Experiments across 32 forecasting tasks show competitive performance with substantially fewer parameters and low computational cost.
Critical strengths
s1. The paper conducts extensive experiments across multiple datasets. The experimental setup and implementation details are well documented, and the proposed method is compared against a broad range of baselines. The related work section also provides a clear discussion of how the method differs from existing approaches.
s2. The paper provides some theoretical analysis to support the effectiveness of the proposed method.
Critical weaknesses
w1: It is difficult to understand the precise problem the paper aims to solve and the core architecture or methodological contribution being proposed. Overall, the paper provides limited insights beyond the empirical results.
w2: TinyCycle appears to be an improvement or an extension of CycleNet. The authors should provide a detailed experimental comparison with CycleNet or clearly explain why such a comparison is omitted.
w3: Although the experiments demonstrate that TinyCycle is lightweight, its predictive performance does not appear particularly impressive. Furthermore, it remains unclear whether TinyCycle can serve as a plug-and-play module to improve the performance of existing models.
Questions for authors
Please refer to the weaknesses.
7 comments
Response to Reviewer xZq1 [2/3]
w2: TinyCycle appears to be an improvement ... why such a comparison is omitted.
Response: Thank you for your mention CycleNet. We have included it in the baseline of our paper. However, we would like to emphasize that TinyCycle and CycleNet differ fundamentally in their underlying assumptions, model architectures, and design objectives.
(1)TinyCycle and CycleNet characterize different aspects of time series. CycleNet repeats a globally learned periodic template and trains a model to fit the residuals, whereas TinyCycle directly uses the context to model the dominant structure of the data. Moreover, CycleNet’s learned global periodicity is distinct from Structure in TinyCycle. The former captures the periodic properties of the dataset itself, whereas the latter is derived from the context and reflects the dominant stable state that the model can capture within that context.
(2) TinyCycle and CycleNet are different types of models. TinyCycle is a lightweight model, whereas CycleNet focuses on improving forecasting accuracy without an explicit lightweight design. The table below compares their efficiency and accuracy. These results will also be included in the revised manuscript.
| Model | MSE ↓ | MAE ↓ | Params ↓ | Train (s) ↓ | Test (s) ↓ |
|---|---|---|---|---|---|
| TinyCycle | 0.321 | 0.345 | 25.25 | 0.526 | 0.063 |
| CycleNet (Linear) | 0.330 | 0.349 | 246,102 | 666.177 | 3.313 |
| CycleNet (MLP) | 0.335 | 0.353 | 545,366 | 903.373 | 4.328 |
(3)The experiments further demonstrate the differences between TinyCycle and CycleNet. Across eight datasets and four forecast horizons (32 tasks; 128 test windows per task), we compare the models through two interventions: shifting the absolute phase index by with observations fixed, and perturbing the 1st (most recent) and 7th historical cycles using paired inputs with matched mean, variance, and cycle-end values. TinyCycle is invariant to absolute phase labels and propagates historical perturbations within the same phase. CycleNet responds to phase shifts and can propagate perturbations across phases, even when its periodic template is set to zero with all other weights unchanged, demonstrating cross-phase propagation through its residual predictor. The table reports medians across tasks: RMS measures normalized forecast changes, while cross-phase energy is the fraction of response energy outside the perturbed phases. Full details are provided in Appendix E3.
| Model | Absolute-phase response RMS | Cycle 1 response RMS | Cycle 1 cross-phase energy | Cycle 7 response RMS | Cycle 7 cross-phase energy | Zero-template cycle 1 cross-phase energy |
|---|---|---|---|---|---|---|
| TinyCycle | 0.000000 | 0.003481 | 0.00% | 0.000651 | 0.00% | — |
| CycleNet Linear | 0.062621 | 0.002057 | 85.61% | 0.001287 | 73.63% | 85.61% |
| CycleNet MLP | 0.023280 | 0.001738 | 87.53% | 0.000958 | 86.90% | 87.53% |
Response to Reviewer xZq1 [3/3]
w3: Although the experiments demonstrate ... serve as a plug-and-play module to improve the performance of existing models.
Response: We have reiterated that TinyCycle was not designed with the primary goal of achieving high predictive accuracy. Nevertheless, TinyCycle outperforms many more complex models. Furthermore, unlike CycleNet, TinyCycle cannot be simply integrated into other models in a plug-and-play manner, as the two approaches fundamentally differ in what they aim to model. However, we acknowledge that plug-and-play integration is indeed effective for certain models.
(1) Performance. We reiterate that TinyCycle is not primarily designed to maximize forecasting accuracy. Its main strength is its lightweight design, while its broader contribution lies in revealing the primary sources of performance in time series forecasting models. While remaining lightweight, TinyCycle achieves lower MSE on the LTSF datasets than models with more parameters, including iTransformer (ICLR 2024), PhaseFormer (ICLR 2026), Toto-2 (arXiv 2026), and MixLinear (ICLR 2026)(Figure 5). On GIFT-Eval, its MASE is second only to xLSTM-Mixer (NeurIPS 2025) among the supervised models compared, and it outperforms first-generation TSFMs such as Chronos (TMLR 2024) and Moirai (ICML 2024)(Figure 16).
(2) Plug-and-play Capability. The core modeling principle of TinyCycle is to map phases to structures. In this paper, we adopt a naive Linear layer to maintain an extremely lightweight architecture, just as a demo. However, this Linear layer can be readily replaced with other architectures, enabling plug-and-play integration. Notably, this modeling paradigm reduces the mapping complexity from to , where , , and denote the lookback window, prediction horizon, and period length, respectively. This reduction improves modeling performance while substantially decreasing the number of parameters. A detailed theoretical proof is provided in Appendix I of the revised manuscript. The following table presents the results obtained by replacing the Linear layer with different backbone models.
| Dataset | Backbone | backbone MSE / MAE | TinyCycle-plug MSE / MAE | Avg. Parameters (Backbone → plug in) |
|---|---|---|---|---|
| ETTh1 | PatchTST | 0.458 / 0.454 | 0.423 / 0.425 | 805,344 → 74,490 |
| ETTh1 | TimeMixer | 0.446 / 0.456 | 0.416 / 0.426 | 89,977 → 61,611 |
| ETTh1 | DUET | 0.428 / 0.443 | 0.435 / 0.428 | 696,141 → 179,032 |
| ETTh1 | iTransformer | 0.457 / 0.466 | 0.427 / 0.434 | 44,080 → 13,834 |
| Electricity | PatchTST | 0.167 / 0.262 | 0.163 / 0.252 | 2,783,504 → 217,666 |
| Electricity | TimeMixer | 0.179 / 0.278 | 0.164 / 0.253 | 347,977 → 179,048 |
| Electricity | DUET | 0.180 / 0.279 | 0.166 / 0.254 | 502,549 → 68,344 |
| Electricity | iTransformer | 0.169 / 0.268 | 0.165 / 0.258 | 482,736 → 358,250 |
| Exchange | PatchTST | 0.388 / 0.418 | 0.373 / 0.410 | 630,920 → 14,482 |
| Exchange | TimeMixer | 0.475 / 0.448 | 0.406 / 0.422 | 906,057 → 60,991 |
| Exchange | DUET | 0.464 / 0.475 | 0.341 / 0.405 | 282,961 → 44,157 |
| Exchange | iTransformer | 0.405 / 0.438 | 0.412 / 0.447 | 110,656 → 57,902 |
For a fair comparison of parameter counts, identical backbone configurations are maintained between the original backbone models and their TinyCycle-plug counterparts. The learning rate is independently tuned for each model to achieve optimal performance on the validation set. Additional experimental results are provided in Appendix I.2 of the revised manuscript.
We hope these responses address your concerns, and we would be happy to provide further clarification during the discussion period.
Response to Reviewer xZq1 [1/3]
We sincerely thank you for your review comments. But we also need to clarify some points:
Response: Thank you for your feedback. We reaffirm the paper’s central research question and approach below and have refined some parts of the paper.
(1) Research question | Which component contributes most to forecasting performance? We want to explain why models with very few parameters can achieve competitive long-term forecasting accuracy. Specifically, we examine how much of the error gap between models comes from recovering the window mean and recurring phase patterns, and how much comes from predicting cross-cycle variations that deviate from these patterns. Overall MSE or MAE measures the size of the error gap, but identifying its sources requires separating these two error components. We now clarify this question and its motivation earlier in the revised introduction (lines 43–53).
(2) Core method | Diagnose errors through Structure–Dynamics decomposition, then use TinyCycle to test the forecasting accuracy that Structure can support. We apply the same phase-based decomposition separately to the ground-truth future and model predictions. Structure consists of the window mean and the phase pattern that repeats across cycles. Dynamics comprises the remaining variation after subtracting Structure, including cross-cycle changes in level, amplitude, and phase. Under the same period and evaluation window, the prediction errors of these two components are orthogonal, so total MSE decomposes exactly into Structure MSE and Dynamics MSE. When comparing two models, the differences in these component errors quantify their respective contributions to the total MSE gap (lines 54–63; lines 193–215; lines 232–244). Based on this diagnostic, TinyCycle tests what forecasting accuracy can be achieved with very few parameters when Structure serves as the main predictive signal. It partitions recent history into aligned cycle blocks and combines same-phase observations using coefficients shared across phases and channels to generate the next block. It then inserts the predicted block into the rolling window, removes the oldest block, and reuses the same coefficients to continue forecasting. The cycle coefficients and boundary-correction coefficient are fitted separately in closed form. The revised Figure 4 caption explains this forecasting process step by step (Figure 4, lines 226–229; lines 259–277; lines 288–307).
(3) Key findings | Dynamics accounts for more remaining error, while Structure more often explains accuracy gaps at distant horizons. In the aggregate results for 720-step forecasts across seven datasets and eleven models, Dynamics accounts for 58.11% of total MSE. However, in the most distant forecast interval in the updated Figure 8 (steps 481–720), the model with lower overall error achieves a larger MSE reduction in Structure than in Dynamics in 96.70% of model pairs (88/91 pairs across fourteen models). These results address two distinct questions: where most forecasting error remains, and where accuracy gaps between models primarily come from. They also explain why TinyCycle can achieve competitive accuracy by focusing on Structure, even when Dynamics remains difficult to predict (Table 8, lines 1400–1403 and 1415–1421; Figure 8, lines 432–450 and 468–477).