- Rating
- 3(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies inference-time sampling and input diversification in frozen time-series foundation models, reporting useful empirical gains but leaving gaps between oracle analysis, practical inference, and the proposed evaluation metric.
Critical strengths
- The paper systematically examines how sampling budget, context length, model size, and input perturbations interact across several TSFM architectures.
- Input diversification offers a simple way to improve frozen models without retraining or changing their architecture.
- Reporting both successful and harmful perturbations provides useful evidence that increased diversity alone does not guarantee better forecasts.
Critical weaknesses
- The theory concerns oracle best-of-N selection using future targets, so it does not establish the benefits of practical median aggregation or label-free strategy selection.
- The paper omits SPRINT (Xu et al., 2026), leaving its positioning and comparative value against existing training-free inference enhancement insufficiently established.
- RobustMSE evaluates a configured inference pipeline rather than an intrinsic model property, while configuration-search costs and unequal candidate-generation costs complicate its claimed fairness.
Xu, L., et al. (2026). See More, Forecast Better and Faster: Enhancing Time Series Foundation Models via Inference-Time Plug-and-Play Downsampling. ICML 2026.
Questions for authors
- How does the method compare with SPRINT (Xu et al., 2026) under matched historical information and end-to-end compute budgets?
- Which reported gains remain when perturbation selection uses only validation data and forecasting requires no access to future targets?
- Can the theory explain median-aggregation gains when the original predictive distribution already has full support?
- How are configurations selected for RobustMSE, and does its budget include configuration search and auxiliary reconstruction calls?
- How much improvement comes from input diversification rather than ordinary multi-sample aggregation when sampling budgets and aggregation rules are matched?
5 comments
Q3. MV Gains under Full Predictive Support
Response. Thank you for raising this point. Full support does not preclude median-aggregation gains: support describes what is possible, whereas the median depends on how probability mass is distributed. The mixture in Eq. (4) can redistribute probability without enlarging support. Section 5.1 explicitly discusses increasing probability mass near the target (lines 346–359).
Let and denote the coordinate-wise population medians. Under i.i.d. sampling and unique, regular medians, the sample medians converge to these respective values. Consequently, if diversified sampling achieves lower asymptotic median-forecast loss even when both distributions have identical full support. This provides a conditional explanation through probability redistribution.
Q5. Marginal Gains from Input Diversification
Table 11 has already demonstrated this contribution by fixing both the sampling budget (N=128) and the aggregation rule (MV). The “None” baseline already performs ordinary multi-sample aggregation; Gaussian diversification changes the inputs while retaining the same number of forecasts and median aggregator. They show meaningful additional gains in several settings while transparently showing that diversification is not uniformly beneficial.
| Chronos-T5 | Standard sampling + MV | Gaussian diversification + MV | Additional MSE reduction |
|---|---|---|---|
| Tiny | 0.1564 | 0.1406 | 10.1% |
| Mini | 0.1523 | 0.1548 | −1.6% |
| Small | 0.1445 | 0.1441 | 0.3% |
| Base | 0.1453 | 0.1431 | 1.5% |
| Large | 0.1481 | 0.1377 | 7.0% |
To further address your concerns, We have added a standard-sampling baseline at (Std@64) alongside the diversified inference results in the main RobustMSE table (Table 3). Std@64 applies MV aggregation to 64 forecasts generated from the unperturbed input, whereas MV@64 applies the same aggregation rule to 64 forecasts generated with input diversification. This comparison fixes both the candidate budget and aggregation rule, directly measuring the marginal benefit of diversification beyond standard multi-sample inference. For a concise comparison, the table below summarizes the dataset-averaged MSE across ETTh1, Traffic, and Electricity. Full dataset-level results and standard deviations are provided in Table 3. The conclusion is that diversified MV achieves lower dataset-averaged MSE in seven of the eight model–strategy comparisons.
| Model | Strategy | MV@64 | Std@64 |
|---|---|---|---|
| Chronos-T5-Base | Task-Agnostic | 0.1326 | 0.1382 |
| Chronos-T5-Base | Task-Specific | 0.1362 | 0.1382 |
| Moirai-1.1-R-Base | Task-Agnostic | 0.1264 | 0.1272 |
| Moirai-1.1-R-Base | Task-Specific | 0.1253 | 0.1272 |
| TimesFM-2.5-200M | Task-Agnostic | 0.1215 | 0.1246 |
| TimesFM-2.5-200M | Task-Specific | 0.1247 | 0.1246 |
| TimeMoE-200M | Task-Agnostic | 0.1130 | 0.1156 |
| TimeMoE-200M | Task-Specific | 0.1131 | 0.1156 |
Dear Reviewer arKv,
Thank you for the time and effort you devoted to reviewing our paper. We would greatly appreciate your feedback on our responses and additional experiments, and we would be happy to clarify any remaining concerns before the discussion period closes.
Best regards,
The Authors
Response to Reviewer arKv
Dear Reviewer arKv,
We sincerely appreciate your careful assessment and recognition of our systematic empirical study. Please find our point-by-point responses below.
W1 & Q2. Distinguishing Oracle Analysis from Label-Free Inference
Response. The manuscript explicitly separates oracle analysis from deployable aggregation. Section 4.1 scopes the theory to best-of-N (lines 238–241), while Section 3 distinguishes oracle EM from inference-time median aggregation (lines 145–159). The theory characterizes candidate-generation headroom; practical MV benefits are evaluated directly.
The relevant gains are the MV results reported throughout the paper, rather than only the oracle EM results. (Q2) For example, Table 11 (lines 1422–1426) fixes both N=128 and MV aggregation. Gaussian diversification reduces Chronos-T5-Tiny’s MSE from 0.1564 to 0.1406 (10.1%), and improves Chronos-T5-Large by 7.0%. These gains require no oracle output selection. Moreover, these are individually reported perturbation results, not merely oracle-selected winners. Our practical claim concerns benefits from specified diversification policies; it does not require solving optimal label-free strategy selection. The default noise policy and optional oracle selector are explicitly distinguished in lines 426–430. Our practical claim is that specified diversification policies can improve median forecasts; it does not require a theorem guaranteeing label-free identification of the optimal policy.
W2 & Q1. Positioning and Comparison with SPRINT
Response. We have conducted additional comparisons with SPRINT and will incorporate its positioning and the new results into the manuscript. (Section 5.3) SPRINT improves inference through trend downsampling, seasonal pattern replication, and forecast reconstruction. Our method instead diversifies the observed context and aggregates predictions from the frozen backbone. Both are training-free, but they modify different components of inference.
Fair comparison. The primary comparison uses the same 512-point contexts, forecast origins, normalization, backbone checkpoints, prediction horizon H=96, and sliding-window stride 32. SPRINT is reimplemented within our evaluation framework. We additionally evaluate valid-edge decomposition, Moirai patch size 16, and a 720-point SPRINT look-back; the latter is a separate sensitivity analysis that gives SPRINT more history.
The new comparisons establish substantial practical value beyond the conceptual distinction. Across Chronos-Base, Moirai-Base, and TimesFM, DSI achieves lower error in all 36 comparisons. This remains true against the best tested SPRINT variants. Representative MV results are (see more results in Section 5.3 of the revised manuscript):
SPRINT requires 4.8–13.2 times fewer inference FLOPs per pass, so equal sample counts are not treated as equal compute. We calculate its affordable sample allocation from the measured FLOPs ratio: Chronos-Base's SPRINT MV errors change little from 16 to 128 samples: 0.1493→0.1477 on ETTh1, 0.1480→0.1484 on Traffic, and 0.4041→0.4014 on Electricity. We also evaluated the cost of the perturbed input of our method in Table 12. The conclusion is that all the cost caused by these perturbed inputs only adds a modest overhead compared to the prediction time.
W3 & Q4. RobustMSE Configurations and Computational Fairness
Response. Evaluating a configured inference pipeline is the intended scope of RobustMSE. The manuscript explicitly states that it measures performance under evaluated inference strategies rather than an intrinsic, strategy-independent model property. Its rankings should therefore be interpreted as protocol-conditioned comparisons. Thus, it can reflect the headroom performance of models under the same protocol.
RobustMSE uses the perturbation settings specified in Table 3 and the empirically screened strategy set described in Section 5.1, which excludes Suffix and Missing perturbations. Task-Agnostic and Task-Specific strategies are evaluated separately. Within each category, the evaluation samples 64 forecasts from the corresponding candidate pool and repeats the aggregation over five trials. Configuration search and auxiliary reconstruction calls are additional costs, but using RobustMSE is fair under the same configuration. Our profiling explicitly measures this difference: Task-Agnostic perturbations add 0.092–0.491 ms/window, whereas reconstruction adds 149.8 ms/window in the current implementation. Equal candidate counts should therefore be interpreted as a controlled sampling protocol, rather than identical computational expenditure across perturbation types.