- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
This paper proposes SpecSpin, a training-free and calibration-free 4-bit quantization method for zero-shot time-series foundation models. The key motivation is that standard LLM-style quantization does not fully fit TSFMs because forecasting errors can compound over long autoregressive horizons, and TSFM attention has exploitable spectral structure. SpecSpin uses three main steps: it applies a DCT transform to q/k/v projections and keeps the highest-energy feature directions, applies a Haar rotation within the retained subspace, quantizes linear layers with NF4, and low-pass filters attention score rows before the softmax. The method is evaluated on Chronos, TimeMoE, and Moirai across six long-term forecasting benchmarks and four horizons. The paper reports that SpecSpin achieves the best average 4-bit performance for all three backbones, with gains increasing at longer forecast horizons.
Critical strengths
-
The paper clearly argues that TSFMs differ from language models because their attention patterns are smooth, recency-biased, and spectrally concentrated, and because autoregressive forecasting can compound quantization error across horizons.
-
The evaluation includes three architecturally different TSFMs: Chronos, TimeMoE, and Moirai, covering encoder-only, autoregressive mixture-of-experts, and decoder-only models. This makes the empirical claim more convincing than testing on a single architecture.
Critical weaknesses
-
The paper compares against BF16, AWQ-4bit, and FQ-4bit, but does not directly evaluate stronger modern post-training quantization methods such as GPTQ, AWQ with calibration, SmoothQuant-style activation handling, QuIP/QuaRot/SpinQuant, or other competitive low-bit methods adapted to TSFMs. This makes it harder to assess whether SpecSpin is superior to strong quantization baselines rather than mainly to simple group-wise quantization.
-
The experiments report each result cell as a single deterministic run, so there is no uncertainty estimate over seeds, quantization randomness, or sampling variability. This is especially important for a quantization paper because the method is intended for deployment, where reliability and predictable accuracy preservation matter as much as average performance. Since some improvements over BF16 or other 4-bit baselines are modest, repeated runs, confidence intervals, or robustness checks across quantization seeds and deployment settings would make the empirical claims more convincing.
-
Some components appear less essential than the method name suggests. The ablation indicates that removing the spin changes average MSE by at most about 0.1% on the tested Chronos settings, so the “Spin” component seems accuracy-neutral rather than a major contributor.
-
The method relies on retention hyperparameters, sometimes tuned per backbone and dataset, which weakens the calibration-free framing. The conclusion notes that retention settings are tuned per backbone and in some cases per dataset, so practical deployment may still require nontrivial hyperparameter selection.
-
The deployment motivation is not fully convincing. Although the paper emphasizes memory-constrained edge deployment, many time-series forecasting workloads can be served in cloud or server settings, and the evaluated TSFMs are not extremely large compared with modern foundation models. The authors should better justify why aggressive 4-bit quantization is necessary for these TSFMs and identify the concrete deployment scenarios where BF16 or 8-bit inference is insufficient.
-
The paper provides useful empirical evidence that TSFM attention has spectral structure and that SpecSpin can exploit it, but the claim is not rigorously established. The spectral sparsity argument rests mainly on observed DCT energy concentration and downstream forecasting results, while the theoretical perturbation bound appears only as a loose sanity check. Therefore, the paper convincingly motivates the method empirically, but it does not provide a strong theoretical proof that SpecSpin generally solves quantization error accumulation in TSFMs.
Questions for authors
-
Can the authors compare SpecSpin with stronger modern post-training quantization baselines, such as GPTQ, calibrated AWQ, SmoothQuant-style methods, QuIP/QuaRot/SpinQuant, or TSFM-adapted variants?
-
Can the authors provide uncertainty estimates or robustness checks? Since each result cell is reported from a single deterministic run, it is unclear how stable the gains are across quantization seeds, model-loading randomness, sampling choices, or deployment settings.
-
What is the practical contribution of the “spin” component? The ablation suggests that removing the spin changes average MSE by at most about 0.1% on the tested Chronos settings. Is the rotation essential for other backbones, lower bit-widths, or harder datasets?
-
How much hyperparameter tuning is required in practice? The paper states that retention settings are tuned per backbone and sometimes per dataset, which seems to weaken the calibration-free framing. Can the authors provide a default setting or sensitivity analysis showing that SpecSpin works robustly without dataset-specific tuning?
-
Can the authors better justify the need for aggressive 4-bit quantization in TSFMs? Many time-series forecasting workloads can be served in cloud or server environments, and the evaluated TSFMs are not extremely large compared with modern foundation models. What concrete deployment scenarios make BF16 or 8-bit inference insufficient?
-
Can the authors strengthen the theoretical justification for why SpecSpin mitigates quantization error accumulation?
3 comments
Weakness 2 and Question 2.
The experiments report each result cell as a single deterministic run, so there is no uncertainty estimate over seeds, quantization randomness, or sampling variability. [...] repeated runs, confidence intervals, or robustness checks across quantization seeds and deployment settings would make the empirical claims more convincing.
Response. Thank you for your comment. We added uncertainty estimates for the two sources of variability in our setting (new App. E.2, Tables 14 and 15, which also include TimeMoE). Inference is deterministic given the weights, and all methods use the mean forecast, so model loading and sampling add no randomness.
- Rotation seed. The Haar rotation is the only random element of SpecSpin. We reran SpecSpin with five seeds at H = 96 and H = 720 (six-dataset average MSE):
| H | SpecSpin mean ± std | RTN | GPTQ | NF4 | |
|---|---|---|---|---|---|
| Chronos-2 | 96 | 0.2296 ± 0.0004 | 0.2331 | 0.2327 | 0.2335 |
| 720 | 0.5100 ± 0.0023 | 0.5201 | 0.5177 | 0.5205 | |
| Moirai 2.0 | 96 | 0.2409 ± 0.0007 | 0.2412 | 0.2413 | 0.2377 |
| 720 | 0.5090 ± 0.0020 | 0.5212 | 0.5438 | 0.5124 |
On Chronos-2 and Moirai 2.0, the seed spread is small compared with SpecSpin's margin over RTN and GPTQ at H = 720 (and at H = 96 on Chronos-2).
- Test windows. Neighbouring test windows overlap, so we use a paired moving-block bootstrap: both methods' per-window errors are resampled with the same blocks of L + H consecutive windows (2,000 replicates). 95% intervals of SpecSpin's relative MSE difference from each baseline, over 6 datasets × 4 horizons (negative = SpecSpin better):
| SpecSpin vs. | RTN | AWQ | GPTQ | Rot.+GPTQ | NF4 |
|---|---|---|---|---|---|
| Chronos-2 | −1.5 [−2.9, +0.04] | −1.5 [−2.9, −0.3] | −1.1 [−2.4, +0.07] | −1.8 [−3.6, −0.3] | −1.5 [−2.8, −0.4] |
| Moirai 2.0 | — | −1.4 [−2.3, −0.5] | −4.2 [−4.9, −3.2] | −5.1 [−5.8, −4.2] | −0.1 [−1.0, +0.3] |
(Bold: SpecSpin significantly better. Moirai RTN: per-window errors were not stored.)
- SpecSpin is significantly more accurate than calibrated AWQ and rotation+GPTQ on both Chronos-2 and Moirai 2.0, than GPTQ on Moirai 2.0, and than NF4 on Chronos-2.
- Its margins over RTN and GPTQ on Chronos-2 are of similar size (−1.5% and −1.1%), with intervals reaching +0.04% and +0.07%. On Moirai 2.0, it matches NF4 alone, with which it shares the quantization grid.
Weakness 3 and Question 3.
Some components appear less essential than the method name suggests. The ablation indicates that removing the spin changes average MSE by at most about 0.1% on the tested Chronos settings, so the "Spin" component seems accuracy-neutral rather than a major contributor.
Is the rotation essential for other backbones, lower bit-widths, or harder datasets?
Response. Thank you for your comment. Following your question, we tested the spin at lower bit-widths and on all backbones. Its benefit is clearest at 3 bits and on the autoregressive backbones.
- Lower bit-widths. We repeated the spin on/off comparison with a 3-bit NormalFloat grid (NF3), built the same way as NF4 (new App. E.4, Table 18). Average MSE change vs. BF16:
| H | NF3 | NF3 +S | NF3 +T+F | NF3 +T+S+F | |
|---|---|---|---|---|---|
| Chronos-2 | 96 | +3.0% | +0.6% | −1.7% | −1.3% |
| 720 | −2.5% | −3.5% | −5.3% | −4.6% | |
| TimeMoE | 96 | +24.4% | +15.0% | +20.6% | +21.6% |
| Moirai 2.0 | 96 | −1.2% | −1.2% | −0.8% | −1.1% |
| 720 | −10.9% | −11.3% | −11.7% | −11.9% |
- On plain 3-bit weights, the spin lowers the error by 2.4 and 1.0 points on Chronos-2 and by 9.4 points on TimeMoE, compared with at most 1.2 points at 4 bits.
- With truncation and the filter, 3-bit Chronos-2 stays 1.3–5.3% below BF16, and on top of these stages the spin adds little.
- Other backbones. We ran all eight on/off combinations of truncation (T), spin (S) and filter (F) on NF4 weights, on all three backbones (new App. E.3, Table 16). Average MSE change vs. BF16:
| NF4 | +S | +T | +T+S | +T+F | +T+S+F (SpecSpin) | |
|---|---|---|---|---|---|---|
| Chronos-2 | −0.1% | −0.4% | −1.1% | −0.9% | −1.8% | −1.6% |
| Moirai 2.0 | −5.1% | −5.0% | −6.6% | −5.9% | −6.1% | −5.3% |
| TimeMoE | +0.6% | −0.3% | +3.4% | +1.4% | +3.2% | +1.1% |
- On TimeMoE, the spin is the stage that helps most, and on TimesFM (App. D.1) removing it raises the error on 5 of 6 datasets, by 1.5–5.7%.
- On Chronos-2 and Moirai 2.0, truncation with NF4 already captures the gain.
We therefore view truncation with NF4 as the core of SpecSpin, and the spin as a stage whose benefit is largest on autoregressive backbones and at low bit-widths. Table 10 reports full SpecSpin because that configuration was fixed before these experiments.
Weakness 4 and Question 4.
The method relies on retention hyperparameters, sometimes tuned per backbone and dataset, which weakens the calibration-free framing.
Can the authors provide a default setting or sensitivity analysis showing that SpecSpin works robustly without dataset-specific tuning?
Response. Thank you for your comment. All results in App. E use one setting per backbone for every dataset and horizon:
-
Chronos-2: (ρ_W, ρ) = (0.90, 0.87).
-
TimeMoE: (0.95, 0.99).
-
Moirai 2.0: (0.90, 0.90).
-
Robustness without dataset-specific tuning. With these fixed settings, SpecSpin remains the best 4-bit method on Chronos-2 and Moirai 2.0 (Weakness 1). On TimeMoE, the fixed setting keeps SpecSpin on par with NF4 alone, and a per-dataset filter setting gives larger gains on Exchange.
-
Sensitivity. The parameter study (App. D.2) varies ρ_W, ρ and the rotated fraction one at a time. Averaged over its three datasets, every truncation level from ρ_W = 0.7 to 0.9 is at least as accurate as no truncation on Chronos-2 and Moirai 2.0. For the filter, the defaults are within 0.3% of no filter (ρ = 0.87 on Chronos-2, ρ = 0.90 on Moirai 2.0) and ρ = 0.7 is within 1.5%, whereas strong filtering hurts (ρ ≤ 0.5 on Chronos-2, ρ = 0.3 on Moirai 2.0, both about +17%).
-
Recommended setting. For a new dataset, we recommend the backbone default. The Chronos-2 and Moirai 2.0 defaults were chosen with the parameter study on ETTh1, ETTh2 and Exchange, and the TimeMoE default on ETTh1. SpecSpin needs no calibration data; its two retention ratios are set once per backbone.
Weakness 5 and Question 5.
The deployment motivation is not fully convincing. [...] The authors should better justify why aggressive 4-bit quantization is necessary for these TSFMs and identify the concrete deployment scenarios where BF16 or 8-bit inference is insufficient.
Response. Thank you for your comment. Our target is devices that must hold the model locally, where storage and memory, not throughput, are the constraint; for cloud or server serving, BF16 or 8-bit inference is often adequate. Examples are gateways and embedded monitors in grids, vehicles or medical devices, where data often cannot leave the device and several forecasters may share a few hundred MB of memory.
- Measurements. We now measure real 4-bit inference with bitsandbytes NF4 kernels (new App. E.5, Table 19). At batch 1, L = 512 (FP = released checkpoint precision):
| H = 96 | Weights (MB): FP / NF4 / SpecSpin | Peak memory (MB) | Latency (ms) |
|---|---|---|---|
| Chronos-2 (FP32 ckpt.) | 455.8 / 79.5 / 79.6 | 476 / 95 / 99 | 69 / 85 / 106 |
| TimeMoE (BF16 ckpt.) | 888.4 / 246.9 / 248.6 | 1291 / 610 / 1037 | 85 / 187 / 359 |
| Moirai 2.0 (FP32 ckpt.) | 43.6 / 5.7 / 6.2 | 97 / 50 / 53 | 101 / 80 / 132 |
4-bit kernels shrink the weights on the GPU by 3.6–7.6× and the peak memory of a forecast by 1.5–5.0×. For example, TimeMoE-200M drops from 888 to 249 MB of weights, and Chronos-2 from 456 to 80 MB. SpecSpin's truncation and rotation add at most 2 MB.
- Latency. At batch size 1, off-the-shelf 4-bit kernels are dominated by dequantization. SpecSpin's weight stages need no custom kernel; its latency is set by the score filter on the unfused attention path (8–92% over NF4 alone), which a fused filter kernel would remove. SpecSpin is therefore best suited to deployments bound by storage or memory.
Weakness 6 and Question 6.
The spectral sparsity argument rests mainly on observed DCT energy concentration and downstream forecasting results, while the theoretical perturbation bound appears only as a loose sanity check. [...] it does not provide a strong theoretical proof that SpecSpin generally solves quantization error accumulation in TSFMs.
Response. Thank you for your comment. We agree with this characterization: the paper provides exact properties of each stage and a stability guarantee, while the link to forecast accuracy is established empirically. Specifically:
- Truncation removes precisely the energy of the discarded DCT directions (Eq. 4).
- The spin is exact before rounding (Eq. 6).
- Proposition 1 bounds the change in the attention output caused by the score filter, guaranteeing that the filter does not amplify error.
The new results support the link to forecast error most clearly on Moirai 2.0, where truncation lowers the NF4 error but leaves the unquantized model unchanged, and SpecSpin's gain grows from −0.8% at H = 96 to −7.8% at H = 720. On Chronos-2, truncation also improves the unquantized model, acting as a spectral regularizer. We will present compounding error as the motivation of the method, supported by these empirical results.
Thank you again for your review. We hope the added baselines, the uncertainty estimates and the component study address your concerns, and we would be glad to answer any further questions.
Thank you for your careful review, and for recognizing the argument for why TSFMs differ from language models and the evaluation across three architecturally different backbones. Below we quote each of your comments and respond to it. Changes in the revised PDF are marked in blue.
Summary of the new results (new App. E). Following your suggestions, we added calibrated AWQ, GPTQ, QuaRot-style rotation and NF4 alone, and ran SpecSpin with one fixed setting per backbone:
Weakness 1 and Question 1.
Response. Thank you for your comment. We added calibrated AWQ, GPTQ, QuaRot-style rotation (+RTN and +GPTQ) and NF4 alone (new App. E.1, Table 10; per horizon in Tables 11–13). The Table 1 "AWQ-4bit" baseline is round-to-nearest and is referred to as RTN; on TimeMoE it now also quantizes the expert gates, routers and output heads.