- Rating
- 3
- Confidence
- 2
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes ReTRN to address the Readout-Gauge Conflict in learned Koopman representations, where different representations may produce identical predicted dynamics but different scientific equation coefficients. ReTRN fixes the scientific equation space, learns an auxiliary neural closure, and uses multi-scale temporal moments to recover governing equations. The authors validate the method through theoretical analysis, targeted interventions, and experiments on multiple dynamical systems.
Critical strengths
The paper explicitly distinguishes dynamical prediction from scientific equation coefficient recovery. Theoretical analysis, targeted interventions, and component ablations support the roles of the fixed equation space and learned closure. Experimental results across multiple dynamical systems further demonstrate the effectiveness of the method.
Critical weaknesses
ReTRN relies on a predefined scientific equation space and relatively restrictive theoretical assumptions. Moreover, accurate coefficient estimation does not necessarily lead to reliable equation support recovery, limiting the method's applicability to unknown dynamical systems.
Questions for authors
- Damped Pendulum achieves an AUPRC of 1, but exact support recovery is 0/10 in Tables 10–11. If the sparsification threshold search range is expanded, can the existing validation criterion select the correct equation without using ground-truth information? Have the authors explored alternative selection criteria?
- Are the identified nonlinear terms and their coefficients stable when the candidate dictionary order or the 10% validation-error tolerance is varied? Does the corresponding long-horizon prediction performance remain consistent?
3 comments
Q2. Do the recovered nonlinear terms and predictions remain stable when dictionary order or validation tolerance changes?
Within the tested cubic-to-quartic expansion, the active nonlinear coefficients remain accurate and three-second predictions improve. Changing the sparsification tolerance leaves the retained coefficient values unchanged and usually leaves the selected support unchanged. The measured heave case also identifies where stronger pruning starts to remove a predictively important nonlinear term.
We varied the polynomial dictionary order from cubic to quartic on seven-observation Duffing and Reaction systems, using five matched fits per setting. The equation heads contain 9/14 and 10/15 functions, respectively. The expanded pipeline also uses next-degree auxiliary closure. All coefficient NRMSE values use the same complete-quartic reference denominator:
| System and | Shared cubic coefficient | Equation NRMSE | 3 s MSE |
|---|---|---|---|
| Duffing 9 | -3.000705 ± 0.000237 | 0.000456 ± 8.95e-05 | 0.000492 ± 7.1e-05 |
| Duffing 14 | -2.999988 ± 0.000040 | 1.44e-05 ± 8.84e-06 | 1.72e-06 ± 2.19e-06 |
| Reaction 10 | -0.998121 ± 0.000229 | 0.001365 ± 0.000436 | 3.13e-06 ± 2.38e-06 |
| Reaction 15 | -1.000215 ± 0.000174 | 0.000141 ± 0.000155 | 3.16e-08 ± 6.97e-09 |
The shared cubic coefficients approach their true values ( and ), and both coefficient and rollout errors decrease in all five matched pairs for each system. Thus, expanding the tested dictionary does not destabilize these recovered mechanisms.
We then varied the short-validation error tolerance from 0% to 25% without coefficient refitting. Retained coefficients therefore remain fixed by construction. The selected supports are identical in 19/20 fits, and one cubic Reaction fit removes small extra terms at 25%. Every true term remains selected, and all 120 three-second rollouts remain finite. At the 10% rule, exact-support counts are 0/5 and 3/5 for cubic/quartic Duffing, and 4/5 for both Reaction orders, showing that the remaining errors involve extra terms.
Does the tolerance preserve the nonlinear dynamics in experimental data? On the measured heave-decay record, the selected equations share the following terms, with and determined by the sparsification tolerance:
$ { \dot{ x }} _ { 1 } = 0.9999633x_{2}$
| Tolerance | Dynamic terms | Validation MSE | Held-out displacement MSE | ||
|---|---|---|---|---|---|
| 0%, 1%, 5% | −87.66034 | −97.80474 | 8 | 1.10765e-5 | 1.77298e-5 |
| 10% | −87.66034 | 0 | 7 | 1.21650e-5 | 1.34112e-5 |
| 15%, 20%, 25% | 0 | 0 | 6 | 1.26964e-5 | 1.44848e-4 |
At 10%, the rule removes while retaining and achieves the lowest held-out MSE among the tested tolerances. At 15%, it also removes , increasing held-out displacement MSE by approximately 10.8-fold relative to 10%. The linear backbone and the other retained coefficients remain stable across these choices. The first three measured records are used for training and validation, and record four is held out intact. This identifies a concrete tolerance boundary for the measured system: moderate pruning retains the recovered nonlinear response, whereas stronger pruning degrades long-horizon prediction.
Thank you for addressing my concerns. I appreciate this theory-motivated work, but given the remaining limitations to its applicability, I will maintain my rating.
We appreciate your recognition of the distinction between accurate dynamical prediction and interpretable equation recovery, as well as the theoretical analysis and targeted experiments supporting ReTRN. We have examined two practical aspects of that distinction: selecting the correct equation support without coefficient truth, and assessing the stability of nonlinear terms under changes in the candidate dictionary and sparsification criterion.
W1 / Q1. Can ReTRN select the correct equation support without ground truth?
Yes, in the tested Pendulum setting, a frozen coefficient-gap selector recovers the exact support, and expanding the original prediction-based threshold grid alone does not. The Pendulum fits achieve AUPRC = 1, so the active terms already rank above the inactive candidates. Their support errors arise when short-validation prediction retains small extra terms. On the original ten fits, expanding the threshold grid under minimum-validation error, 1/5/10% parsimony, or one-standard-error selection still gives 0/10 exact supports.
To use the information in that ranking, we normalize coefficient magnitudes by the largest coefficient of each output, pool the positive normalized magnitudes, and place the threshold at the largest adjacent multiplicative gap whose geometric midpoint lies in [10−4,0.30]. The rule and ReTRN configuration were frozen before 20 new independent seven-observation Pendulum replicates were generated. We apply it to each candidate head/closure split, select the split using disjoint short validation, and evaluate frozen equations on 32 new three-second trajectories per replicate. Neither true coefficients nor long tests enter selection, and no coefficient refitting is used.
The result directly answers the support-recovery question: the frozen gap rule removes all false positives across 20 new replicates, whereas the ordinary validation criteria retain extra terms. All four selectors retain every true term. The gap-selected equations have lower coefficient error, while their mean three-second prediction MSE is higher (2.03e-07 versus 2.16e-08 for minimum validation). This quantifies the trade-off between exact equation structure and finite-horizon prediction error.
Does the gain come from the threshold or from choosing a different fitted model? We held each replicate’s fitted model fixed and applied both threshold rules to the minimum-validation candidate (Mval) and the gap-selected candidate (Mgap):
For either fixed model, gap thresholding recovers 20/20 exact supports, establishing that the improvement in structural selection comes from the cutoff rule itself. Choosing the fitted representation still matters for parameter and prediction accuracy: under the same gap rule, the selected NRMSE is 6.78e-4 for Mval and 8.70e-5 for Mgap. The complete gap-based procedure jointly selects a suitable representation and its sparse equation. The candidate equation library remains predeclared. For uncertainty over nested choices of U, Appendix A.5 uses a frozen short-validation warning-and-abstention rule: it accepted 39/40 independent deployments, and every accepted space contained all true terms on post-freeze inspection. This assesses candidate-space adequacy within the tested families, complementing the support-selection result above.