- Rating
- 2
- Confidence
- 2
- Informativeness
- 2(+1)
- Presentation
- 2(+1)
- Soundness
- 2
Read review
Paper summary
This paper introduces Variational Surrogate Jacobian (VSJ), a theoretically-motivated rule for how to backpropagate gradients through optimization-solution mappings, using a surrogate Jacobian, despite the actual mapping having zero or undefined gradients. The proposed class of surrogate Jacobians admits parameterizations which reproduce various other commonly used surrogate Jacobians, and acts as a generalized version. Sweeping over various hyperparameters (choice of M, Omega, and P) results in improved surrogate Jacobians, which when used for learning, increase benchmark scores on various optimization problems.
Critical strengths
- Sweeping the possible VSJ configurations produces surrogate Jacobians with improved performance over baselines.
- VSJ does not introduce a huge number of hyperparameters in order to be able to reproduce existing backward rules.
Critical weaknesses
- Clarity: The paper is difficult to understand.
- Proliferation of names and shorthands: By pages 8 and 9, there are too many terms lacking clear definitions which make the takeaways difficult or impossible to extract. Examples include "native" (line 361), "SPO+", "Blackbox", "cost reflection", "loss-gradient probing" (line 409), "loss-dependent updates" as a whole from lines 409 to 417, "starting recipe" (line 450), "matched strict-adaptive controls" and "native enforcement" (lines 450-451). The text explaining benchmark results is embedded with many numbers that are hard to contextualize.
- Proliferation of symbols: New symbols are introduced at various points which are barely used elsewhere in the writing, rather than writing their definitions in-place directly, causing excess confusion, especially when the definitions are not present. Examples include , , and from Table 1, from line 303. It is unclear where (line 296), (line 300), and (line 300) come from.
- The problem setups of the benchmarks are underexplained and lack Figures. It is totally unclear from the main text what kind of optimization problem is set up from the benchmark description, how the learned predictor is used to pick the optimization parameters, and how the solution gets mapped to a loss, not to mention how a discrete solution is picked in the forward pass when the problem is a discrete optimization problem. Without these details, the many numbers embedded in the text in Section 5 lack context.
- Motivations for various mathematical manipulations in Sections 1 and 3 are not clear before the manipulations are performed. E.g., Why do we choose to hard-enforce for one part of the derivation (page 2, line 095) only to declare the hard-enforcement an issue (line 214) so to walk back on that decision in order to derive VSJ? It would be easier to follow if the assumptions required for deriving VSJ did not change as we derive it.
- Lack of context on what function is used in various situations.
- There is too much focus on the correctness of reproduction of other existing backward operators in the literature. It's not that hard to believe that the reproduction is correct, and the amount of tables, derivations, and numerical matching tolerances embedded in the text devoted to showing this correctness is distracting.
- Alarming and unexplained mention of a "seed collapse" phenomenon on line 415, and also a mention that some ablations still remain to be tested (line 451).
- There is no uniformly best selection of for every problem, and the issue of picking the best algorithm to solve the benchmark is not reduced by the introduction of VSJ.
- Line 419 instructs the practitioner that the practical method to retain settings from methods other than VSJ, and then tune hyperparameters.
- Unlike OptNet (Amos & Kolter, 2017), VSJ does not provide gradients towards optimization problem components other than the objective, such as the constraint parameters.
Questions for authors
- Why do different algorithms produce different results at all here? If I understand correctly, some of the benchmarks (Knapsack, Portfolio optimization problems) are under-parameterized, meaning with enough training, all converging algorithms using any Jacobians should all recover the same solution with the same loss, given that the feasible set and objectives are all convex. Are they fundamentally not guaranteed to all reach the same minimum in the end, or rather are the solutions under-trained, or is one of my assumptions wrong, such as the solution being discrete?
- What is the "seed collapse" and why does it happen? How often does it happen?
7 comments
Response to Reviewer frUZ (2/4)
2. Proliferation of symbols
The reviewer points at three different problems, and we fixed each differently. We also added a new Notation section in appendix.
Symbols with no visible origin (τ at line 296; ε and µ_Log at line 300). None of these is a VSJ quantity. Each is the strength of the regulariser R in Eq. (1) that the corresponding existing method adds: τ for SparseMAP's quadratic term, ε for the entropy term, and µ_Log for the log barrier.
We had written those regularisers out only in Appendix F (Eqs. 105, 110, 113), so the main text showed their Hessians without their source. Tab. 1 now lists each regulariser beside its Hessian, so every symbol in the table is defined in the table:
| Method | Regulariser R(s) in Eq. (1) | Curvature H_R = ∇²R(s⋆) | (P, M, Ω) |
|---|---|---|---|
| Identity Update | 0 | 0 | (−I, I, 0) |
| SparseMAP | (τ/2)‖s‖² | τI | (−H_R⁻¹, H_R, I) |
| OptNet | ½ sᵀQ_θs | Q_θ | (−H_R⁻¹, H_R, I) |
| Entropy-KKT | ε Σᵢ sᵢ(log sᵢ − 1) | H_Ent = ε diag(1/sᵢ⋆) | (−H_R⁻¹, H_R, I) |
| Log-barrier KKT | −µ_Log Σᵢ log sᵢ | H_Log = diag(µ_Log/(sᵢ⋆)²) | (−H_R⁻¹, H_R, I) |
| PEAR (quadratic base) | ½ sᵀQ_θs | Q_θ | (−H_R⁻¹, H_R, I) |
Here τ, ε and µ_Log are positive and are each method's own regularisation strength. Q_θ is the positive-definite quadratic-cost matrix of the QP, which OptNet may learn.
Symbols used once (e at line 303). The prediction error e appeared in a single sentence, together with g_PEAR and c. We removed all three from the main text and state the fact in words: PEAR's regret gradient applies the same Jacobian to the cost-prediction error. The derivation stays in Appendix F.
Symbols we kept (Q_θ, H_Ent, H_Log). We respectfully note that these are not single-use. They are the values of the prior and metric axes, and they label Fig. 1(c), Tab. 1, Tab. 3 and the appendix tables (Tabs. 20, 21 and 23–25).
3. Benchmarks are underexplained and lack Figures
We have now added Figure 3 to illustrate the five benchmark pipelines: input data → learnable predictor → predicted optimization inputs → evaluation solver → decision. Each panel specifies predictor dimensions, continuous or binary decision domains, and the objective and constraints. This complements:
- Figure 1(a), which shows how decision outputs feed a downstream loss and how surrogate Jacobians enable backpropagation.
- Appendix H.1 (Formulation of the Benchmarks), which provides the mathematical formulations of all five main benchmarks, including their optimization objectives, constraints, and continuous or binary decision domains.
- Appendix H.2, which defines the evaluation metrics and explains how the resulting decisions are scored.
4. Why do we choose to hard-enforce F δs = 0 for one part of the derivation (page 2, line 095) only to declare the hard-enforcement an issue (line 214) so to walk back on that decision in order to derive VSJ? It would be easier to follow if the assumptions required for deriving VSJ did not change as we derive it.
We apologize for not making this progression clear. The assumptions in fact do not change during the derivation. To clarify, we first derive Strict VSJ, where preserves the selected active manifold to first order. However, an inequality can remain satisfied without remaining tight, so this preservation can overly restrict updates. Adaptive VSJ therefore generalizes the construction by softening inequality enforcement in the backward rule, while keeping equalities exact. We now explain this motivation explicitly in the Introduction, before the detailed derivation in Section 3, to clarify that the Adaptive VSJ broadens the surrogate family rather than reverses an assumption.
We also included further clarification such as including Adaptive VSJ as a definition, and adding more intutions to equations.
5. Lack of context on what R function is used in various situations..
When we introduce function in Eq.(1) of Sec.1, we include more intuition and examples. Specifically, we mention that "Setting gives a linear objective, while quadratic (Amos & Kolter, 2017) or entropic (Agrawal et al., 2019) choices give the regularized problems considered later."
Response to Reviewer frUZ (3/4)
6. Too much focus on the correctness of reproduction of other existing backward operators
We would like to kindly clarify that these experiments (in Section 5.2) are not merely reproductions of baseline performance. VSJ provides a single variational construction in which existing backward operators arise as particular choices of the prior, metric, and constraint weights. Section 5.2 therefore checks whether selecting those configurations in the unified VSJ implementation recovers the corresponding native operators, examining both operator agreement at matched problem states and end-to-end consistency. Therefore, this directly supports the framework’s unification claim and provides a controlled reference for evaluating new configurations.
frUZ.2 What is the "seed collapse" and why does it happen? How often does it happen?
What is collapse? Intuitively, the convolutional network (that is supposed to learn the mapping from the country flags to their locations on the globe), maps different countries into an almost point-like configuration, instead of learning their relative locations. This is a previously documented difficulty, not a failure introduced by VSJ. For example,
- Original Blackbox paper, Appendix A.3.3, also identifies nearly coincident city locations as problematic local minima and introduces a repellent loss to push the locations apart
- Sahoo et al. (2023, Section 4.4, Figure 4(c)) report that “cost collapse occurs quickly for BB, but not for Identity” under gradient perturbations, after switching off their additional margin-inducing cost noise.
How often does it occur? To quantify this behaviour and investigate its mechanism, we extended the TSP comparison from 5 to 20 paired seeds, evaluating SPO+ and Blackbox with and without their selected VSJ configurations. We retain every seed and distinguish three observed outcomes by the fraction of test instances decoded to an optimal tour:
- Collapsed: 0% optimal tour predictions from the model.
- Stalled: >0% but less than 50% optimal tour predictions.
- Regular: at least 95% optimal tour predictions.
Collapse is therefore the more severe failure: no test instance receives an optimal tour, rather than training attaining only partial success.
VSJ substantially reduces the observed failure frequency: We have noted that no collapse occurs with either selected VSJ configuration, and SPO+ stalling decreases from 11 to 5 runs.
| Method | Collapsed | Stalled | Total unstable runs |
|---|---|---|---|
| Native Blackbox | 4/20 (20%) | 0/20 | 4/20 (20%) |
| Blackbox + VSJ | 0/20 | 1/20 (5%) | 1/20 (5%) |
| Native SPO+ | 0/20 | 11/20 (55%) | 11/20 (55%) |
| SPO+ + VSJ | 0/20 | 5/20 (25%) | 5/20 (25%) |
Does this improve performance? Yes. Across all 20 seeds, mean relative test regret decreases (lower-better):
- Blackbox: from to .
- SPO+: from to .
Thus, improved training reliability is reflected in better performance.
How does this relate to the theory? As discussed in Section 4.2, differences of feasible decisions preserve shared affine equalities but need not be tangent to selected active inequality or bound constraints. VSJ controls their enforcement through and the correction geometry through . The observed reductions in collapse and stalling, together with lower all-seed regret, provide empirical evidence of improved training reliability with the selected VSJ configurations on this benchmark, consistent with this motivation.
Manuscript change: Having provided an in-depth analysis, we now report the main-paper TSP comparison over 20 seeds without excluding unsuccessful runs for loss-dependent updates. We have also added a detailed discussion in Appendix H.9 for the collapsed and stalled cases.
frUZ.3 — Apparent unfinished ablations
We apologize for the ambiguous wording. “Native enforcement remains worth testing” refers to the experiment we had already completed and included in the initial submission to highlight Strict VSJ's performance in Table 5. With this sentence, we wanted to emphasize that Strict VSJ, in fact, performs better than Adaptive VSJ for time-series Portfolio in Table 5. To clarify, we have now replaced that sentence with: “The Strict VSJ and Adaptive VSJ rows of Tab. 5, which differ only in , show why strict constraint enforcement should remain a candidate when configuring VSJ.”
Response to Reviewer frUZ (1/4)
We sincerely thank Reviewer frUZ for the detailed, line-level feedback and for recognizing the improved backward configurations obtainable within VSJ’s compact parameterization. Your comments have guided revisions to terminology, notation, benchmark illustrations, and the motivation preceding the mathematical construction. We believe that the presentation of the paper improved quite notably. We also clarify few misunderstandings in our reply. We hope the revised manuscript, additional evidence and our further clarifications address your concerns. If so, we would be grateful for a reassessment. Please find our detailed responses below.
frUZ.1 Clarity concerns.
We thank the reviewer for the line-level detail, which made this weakness directly actionable. These concerns are not difficult to address, and doing so significantly improves the readability of the paper. Section 5 now defines every term at first use, and Section 4.1 now defines each symbol where it appears.
The revision addresses all points (clarity on names and shortands, the proliferation of symbols, the lack of benchmark figures, more motivations on equations). Importantly, none of results in the paper changes.
1. Proliferation of names and shorthands. Every term the reviewer lists is now defined at first use, and Section 5 now has a short terminology paragraph.
Also within this scope: