- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
Paper investigates three roles of patches in autoregressive forecasting: input representation, transition length, and execution width. It introduces ATD to generate multiple future patches per model call and Spectrum Tangent to correct accumulated forecasting errors using periodic history. Experiments report up to 5.54x faster inference with similar accuracy, alongside modest long horizon improvements.
Critical strengths
The separation of transition learning from execution width is useful and practically relevant. ATD provides substantial measured speedups while preserving forecasting quality. The matched comparisons distinguish trajectory imitation from actual prediction accuracy, and experiments with AutoTimes, Timer,and TimesFM provide additional evidence of transferability.
Critical weaknesses
main concern is limited methodological novelty. Multioutput decoding and trajectory distillation build on established approaches, while Spectrum Tangent is essentially a fitted correction toward a periodic history template. Its additional contribution over simpler seasonal correction methods is not clearly established. empirical claims also require qualification. The reported 5.54x speedup is measured on local models, without corresponding end to end timing on the three external forecasting backbones. Spectrum Tangent provides relatively modest average improvements and deteriorates on Exchange Rate, indicating sensitivity to data characteristics. The evaluation also relies on only three training seeds.
Questions for authors
Can the authors clarify how Spectrum Tangent compares with simpler seasonal or residual correction baselines under matched conditions? Do the reported inference speedups persist on the external pretrained models? Can the authors identify conditions under which the periodic correction is likely to degrade performance?
3 comments
Dear Reviewer WCWK,
With the discussion period closing shortly, thank you again for your constructive review. We would like to gently check whether our added baselines and timing results address your questions:
- Matched correction baselines (Appendix C, Table 24): Added closed-loop and open-loop comparisons against History Mean, Last Cycle, SteerCast, UEC-STD, and BOOST on frozen serial Timer (Tangent achieves the lowest MSE on 4/5 datasets in each mode).
- Public-parent batch-128 speedups (Appendix C, Table 23): Confirmed end-to-end ATD-8 speedups under native cache settings (– on Timer, – on TimesFM, – on AutoTimes).
- Boundaries & seeds (Secs. 4.5–4.6, 5 & Appendix C, Table 26): Added chronological block diagnostics and explicitly qualified Exchange/ETTh2 failure cases and seed checks.
Please let us know if any questions remain. Thank you for your time.
The added correction baselines and failure case diagnostics substantially address my empirical concerns and clarify the scope of the claims. While methodological novelty remains modest and seed coverage limited, the practical contribution supports retaining my weak-acceptance recommendation.
Residual-correction baselines and public-parent speedups
Thank you for recognizing the value of separating transition learning from execution width. Under patch-role coupling (p0/P/K), we conduct three targeted studies—two separate decouplings (local input scale and commit width) plus a correction motivated by ATD's inherited parent residuals—using minimal instruments to test whether local encoding can be fixed, frozen trajectories compressed, and inherited residuals corrected.
1. Contribution and correction baselines
Spectrum Tangent tests whether a single train-calibrated history direction reduces inherited residuals in closed loop, hence the uncorrected-forecast baseline. R2 adds your requested seasonal and residual baselines; Tangent achieves the lowest MSE on 4/5 datasets in both modes.
R2. MSE change (%) vs. uncorrected frozen serial Timer (W=672, H=720); first 96-point block protected. Closed loop writes predictions back; open loop acts on fixed proposals.
Per series, history mean uses the lookback mean, last cycle tiles the final lookback cycle, and Tangent averages matching phases across cycles. All templates share the train-selected period, ramp, 384 training origins, and one fitted nonnegative scalar. SteerCast uses the matched mask, UEC-STD validation adaptation, and BOOST five Timer lags. UEC-STD/BOOST are evaluated open-loop as post-hoc baselines lacking a Timer patch-writeback rule; Tangent is shown in both modes.
2. Public-parent speedups
Yes. Native-path ATD-8 speedups hold fixed parent and cache policy: 2.87–3.54× (Timer), 2.09–2.11× (TimesFM), and 7.83–7.96× (AutoTimes).
R1. ATD-8 P50 speedup over serial parent (batch 128, W=672, H=720, RTX 5880 Ada): native KV reuse / cross-call KV disabled (AutoTimes uses native re-encoding).
3. Gain size, consistency, and failure cases
We agree average gains are modest; Tangent's contribution is showing that long-horizon AR residuals retain exploitable structure along a simple periodic history direction. At H720, it lowers MSE by 2.54% over local ATD across all 42/42 runs (14 dataset–width configs × 3 seeds) with zero added parameters/calls and 3.24× pipeline speedup (Table 2b). R2 confirms this on frozen serial Timer (4/5 datasets, −2.85% to −21.07% MSE), showing a consistent yet bounded effect.
R4(a). Frozen serial Timer (H=720) across chronological test blocks; ΔMSE (%) vs. uncorrected Timer.
On frozen serial Timer, the correction direction is negatively aligned with Exchange test residuals in all four blocks (pooled cosine −0.4197), raising closed-loop MSE by 0.97%. ETTh2 blocks 2–3 show positive alignment but step overshoot on fixed proposals; block 1 shows writeback reversing a fixed-proposal gain. In the submitted local ATD-4/8 Exchange runs, the training-selected correction (τ∗=12, α∗≈1.50 vs. 0.085–0.482 on the seven periodic sets) passed all six held-forward training checks but increased H720 test MSE at both widths. The revised PDF adds R1, R2, and R4(a) in Appendix C (Tables 23, 24, 26) and highlights Secs. 4.5, 4.6, and 5 in blue.
On seeds: the selector fits on training blocks 1–3 and confirms on block 4; leave-seed-out and no-pooling controls pass 42/42 held-forward checks with matching periods, and named-parent Tangent improves 36/36. Mean four-horizon MSE seed std is 0.0016/0.0017 (ATD-4/8) vs. 0.0069/0.0124 (Joint Direct); serial Timer uses one frozen checkpoint evaluated by blocks.