- Rating
- 2
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Observer State-Space Models (OSSMs) for time series forecasting, motivated by the mismatch between observation-driven recurrent dynamics during the context window and free-running dynamics during forecasting. OSSM interprets observations as measurements that correct an autonomous latent state rather than as control inputs that determine its evolution. The authors connect this formulation to Luenberger observers, show that conventional closed-loop SSMs can be viewed as entangled instances of OSSM, and conduct a large controlled comparison across 14 datasets and 5,376 matched runs.
Critical strengths
- The paper provides a simple and well-motivated conceptual contribution: separating autonomous state propagation from observation-based state correction.
- The connection to classical observer theory gives the architecture a meaningful dynamical interpretation rather than introducing an ad-hoc forecasting module.
- The comparison with SSM is carefully controlled: encoders, parameter counts, seeds, optimization settings, and data splits are matched, with only the prediction-head parameterization changed.
Critical weaknesses
- Since OSSM and the closed-loop SSM are functionally equivalent model classes, the paper could characterize more precisely why the OSSM parameterization is easier to optimize. Currently, this is mostly inferred from the empirical results.
- The experiments focus on comparing OSSM with its matched SSM counterpart. This is appropriate for isolating the proposed principle, but leaves its competitiveness within stronger modern forecasting architectures less explored.
- OSSM receives an additional initialization constraint on the observer-error dynamics, , whereas the SSM baseline only matches the free-running spectral radius. This makes it difficult to fully separate the benefit of the parameterization from the benefit of the initialization strategy.
Questions for authors
- Can the authors provide an ablation separating the effect of observer parameterization from the additional spectral initialization of ?
- Since OSSM and closed-loop SSMs represent the same function class, can the authors further analyze the optimization landscape or gradient conditioning to explain why OSSM converges more reliably?
2 comments
W2.
To complement Appendix B, we also tested the observer formulation within the original SpaceTime architecture, preserving its architecture and parameter budget. This preliminary study, based on short-term datasets (reported in the global response), provides evidence that the observer formulation is not tied to vanilla SSM. A comprehensive comparison with all modern forecasting architectures is indeed beyond the scope of the current controlled prediction head-level study.
We sincerely thank the reviewer for the constructive assessment and for recognizing the motivation, observer-theoretic interpretation, and controlled evaluation. Your questions motivated a four-variant, function-matched ablation and a theoretical and empirical analysis of optimization. We summarize the most relevant findings below.
Q1.
We agree that matched initialization provides a direct way to disentangle the effects of parameterization (how OSSM explores the optimization landscape) and spectral initialization (how control theory guides the starting dynamics).
We therefore conducted the requested ablation using four variants:
The experiments cover the 14 datasets, four architectural configurations, multiple forecasting horizons, three seeds, and constant learning rates (10−5,10−4,10−3), alongside the original training schedule.
Matched variants share identical initial predictions, seeds, and batch ordering. We additionally monitor gradient evolution, effective transition matrices, spectral radii, innovation residuals, and optimization failures.
Some results at the paper's training setting:
Gains are averaged across five forecasting metrics.
The experiment demonstrates that the OSSM parameterization improves forecasting while both heads start from exactly the same function. The complementary initialization comparisons show a dataset-dependent effect: observer initialization helps on Traffic and Electricity but hurts on NYSE. Hence initialization alone does not explain OSSM's gains. Please find the setup and dataset results in the common response. Below, we provide further evidence of the different optimization trajectories induced by its parameterization.
Q2.
The above mapping is a bijection, so both heads represent exactly the same functions. They differ in which matrix a gradient step moves the most.
The prediction-head uses two transition matrices:
Because the forecast matrix is applied several times, the loss is most sensitive to it.
Key point. A matrix built from several parameters moves faster under a gradient step, because the updates of all its parameters add up. In function space, the parameterization therefore acts as a preconditioner. It amplifies the step by 1+σmax(G)2+σmax(C)2, where G is the gain (BS or LO), and σmax the largest singular value. This factor is ≃ 6 from the SSM initialization.
Evidence from matched pairs (same initial function).
We observe, from the above table, that:
The experiments and the theory support that OSSM gradients are better conditioned, explaining why OSSM converges more reliably, especially on long-term datasets.
These additional analyses will be part of the updated paper.