- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents LAPANDA, a matrix-free differentiable solver for nonconvex constrained optimization. The forward pass combines ALM with the first-order PANDA solver, while the backward pass approximates optimizer sensitivities using those of the final ALM subproblem. The paper establishes local convergence guarantees and a sensitivity error bound. Experiments demonstrate promising improvements in runtime and memory efficiency.
Critical strengths
- The work addresses an important bottleneck in differentiable optimization and provides a practical, cross-platform implementation suitable for resource-constrained deployment.
- The matrix-free approach for general nonconvex constrained programs avoids explicit matrix factorization, relying on operator-based derivatives for efficient forward and backward computation.
- Experiments demonstrate substantial improvements in runtime and memory usage over the tested baselines.
Critical weaknesses
- The theoretical guarantees rely on strong regularity assumptions and do not cover degenerate cases. Moreover, finite-penalty sensitivity errors may persist even after forward convergence.
- The rectangular-obstacle formulation violates LICQ, raising concerns about the reliability of the computed sensitivities.
- Some comparisons use inconsistent convergence criteria. Additionally, the failure of acados may stem from the degenerate constraint formulation and initialization.
- The method largely integrates established ALM and PANDA frameworks, while the individual contributions of these components are not sufficiently investigated.
Questions for authors
- Could the authors provide ablations with alternative inner solvers to isolate PANDA's contribution?
- How sensitive are the gradients to penalty parameters, convergence tolerances, and problem conditioning? Does performance degrade on ill-conditioned instances?
- Could the authors compare solvers under matched accuracy criteria? How does acados perform on the rectangular-obstacle task with feasible warm starts or a nondegenerate constraint formulation?
4 comments
Reponse to reviewer ge4q (2/2)
Q3. Comparison criteria and the rectangular-obstacle experiment.
As discussed under W3, the overall sensitivity error has several sources. Matching it across all the compared solvers—CasADi/IPOPT, SafePDP, acados and TurboMPC—is difficult. We use common requested forward tolerances within each task. However, the factorization-based backward computations in CasADi/IPOPT, SafePDP and acados typically produce much smaller linear-solve errors than loosely stopped iterative methods such as lapanda and TurboMPC. lapanda-ALM additionally incurs finite-penalty bias. A common numerical backward tolerance therefore would not match gradient accuracy.
We instead compare cumulative complete solver-call wall time to the same recorded training-loss target, using appropriate backward settings for each method:
| Task | Target loss | lapanda-ALM (s) | lapanda-KKT (s) | CasADi/IPOPT (s) | SafePDP (s) | acados (s) | TurboMPC-CPU (s) |
|---|---|---|---|---|---|---|---|
| CartPole/OL | 0.5 | 2.45 | 2.60 | 138.63 | 255.35 | 99.01 | — |
| CartPole/CL | 0.03 | 14.01 | 14.04 | NR | NR | 61.28 | — |
| Quadrotor/OL | 190 | 18.66 | 19.28 | 130.88 | 210.56 | 47.05 | 342.89 |
| Quadrotor/CL | 2.3 | 12.77 | 13.36 | 187.70 | 288.73 | 113.27 | 396.38 |
| Robot arm/OL | 1 | 9.99 | 10.19 | NR | NR | 56.62 | 564.92 |
| Robot arm/CL | 0.03 | 5.54 | 5.70 | NR | NR | 305.69 | 209.47 |
NR denotes a target not reached within the prescribed training run; — denotes unsupported.
Under these settings, both lapanda strategies reach all six targets with low computation and memory costs. Their complete-solver memory is 3.5–5.0 MiB, compared with 56.2–277.4 MiB for these external baselines.
Appendix B.6, Step 3 also analyzes approximate stationarity under bounded absolute gradient errors for ordinary gradient descent. Under its stated assumptions, this provides theoretical support for using controlled inexact gradients in outer optimization.
The original manuscript already included a smoothed rectangular-obstacle experiment with feasible initialization and shifted warm starts in Appendix C.3, with a pointer from the main text. Both methods successfully avoid the obstacle in five 30-step MPC rollouts. The updated timings are:
| Timed MPC calls after initialization | lapanda mean wall time (ms) | acados mean wall time (ms) |
|---|---|---|
| All 30 steps | 1.127 | 9.705 |
| Excluding the first step | 0.689 | 9.982 |
Thank you for the additional experiments. However, my main concerns regarding sensitivity reliability under ill-conditioning and the limited methodological novelty are not fully addressed. In particular, the additional error analysis helps explain the limitations but does not fully resolve my concerns about the reliability of the computed sensitivities in practice. Therefore, I will maintain my original rating.
Response to Reviewer ge4q
We understand the reviewer's concerns about sensitivity reliability, ill-conditioning, and methodological novelty. Our latest revision strengthens the connection between the subproblem structure, gradient errors, and outer learning. We summarize the main additions below.
1. Reliability: connecting the approximation error to outer-learning convergence.
Building on standard inexact-gradient optimization analysis, we have expanded Appendix B.6 to study how the subproblem approximation affects learning. For the squared-residual imitation objective, we derive
\le b_{\rho,\tau_B}\|r_{\mathrm{out}}\|+\delta_F, \qquad b_{\rho,\tau_B}=O(\rho^{-1})+O(\tau_B),$$ under the stated regularity and uniform boundedness assumptions. Here, $r_{\mathrm{out}}$ is the imitation residual, $\tau_B$ is the backward residual tolerance, and $\delta_F$ accounts for additional forward-point errors. This reveals a useful structural property: the absolute gradient bias from subproblem differentiation is modulated by the learning residual. Consequently, at a finite penalty, this contribution can decrease as the imitation residual decreases. The analysis thus goes beyond a pointwise sensitivity-error bound and explains why approximate subproblem gradients can remain useful during learning. We further establish a finite-iteration approximate-stationarity guarantee for the projected normalized update used in our experiments, with a neighborhood controlled by the update step and total gradient error. For ordinary gradient descent, additional local gradient-dominance assumptions also yield local loss convergence for realizable imitation objectives. These results connect the method's error structure to outer optimization, while distinguishing the guarantees for the two update rules. **2. Conditioning: a shared challenge in constrained sensitivity computation.** Ill-conditioning can amplify not only the finite-penalty bias, but also forward-solve and backward-solve errors. This is a shared numerical challenge in constrained sensitivity computation. To provide additional context, Table 8 now also reports acados's final-batch learning-gradient discrepancies against independently re-solved high-accuracy NLP references: | Task | lapanda-ALM | lapanda-KKT | acados | |---|---:|---:|---:| | CartPole/OL | 0.015% | 0.007% | 0.003% | | CartPole/CL | 0.458% | 0.115% | 2.932% | | Quadrotor/OL | 0.065% | 0.402% | 1.168% | | Quadrotor/CL | 0.239% | 0.144% | 1.522% | | Robot arm/OL | 0.119% | 0.010% | 0.167% | | Robot arm/CL | 14.200% | 10.830% | 2.448% | Errors include both forward and backward effects, evaluated at each method's own final batch. † Some reference points do not pass all qualification checks; these full-batch entries are diagnostic rather than fully qualified accuracy estimates. The numerical difficulties in the Robot arm setting also affect other solvers; the discrepancies can additionally involve forward-point and solution-branch differences. Appendix B.6 explicitly identifies the amplification factors, while Appendix C.4.1 isolates these effects in controlled experiments. Preconditioning and related techniques are worthwhile directions for improving robustness to ill-conditioning. A general solution to this challenge is beyond the focus of this paper, and we identify it as a limitation. **3. Novelty: a matrix-free framework for general constraints, with a structure–error–learning analysis.** Our contribution is a matrix-free differentiable framework for general smooth equality and inequality constraints, together with a systematic study of its backward computation. Within the ALM–PANDA framework, we establish the sensitivity relationship between the original problem and the final subproblem, characterize structural and numerical errors, and connect those errors to outer learning. Original-KKT differentiation provides an accuracy-oriented option and a reference for the subproblem approximation; the latter exploits a smaller, locally positive-definite adjoint system for additional computational savings. The experiments evaluate this trade-off at both levels. Rosenbrock compares backward accuracy, time, and memory at shared forward points, including accuracy-calibrated KKT comparisons. The OCP experiments evaluate complete solver-call time to common loss targets and separately report backward costs. Across the six OCP protocols, the subproblem strategy reduces cumulative backward time by **15.5%** and sampled peak backward allocation by **7.5%** on average relative to our original-KKT implementation. These results demonstrate the practical value of exploiting the subproblem structure when its gradient accuracy is sufficient for the learning task.
Reponse to reviewer ge4q (1/2)
We thank the reviewer for the feedback on our method and experiments, especially the concerns about sensitivity accuracy. We have expanded the error analysis and added experiments to address these concerns.
W1. Regularity assumptions and finite-penalty errors.
We have emphasized in the main text that the lapanda-ALM backward strategy offers a trade-off between sensitivity accuracy and computational efficiency, and discussed it in the limitations. Its finite-penalty bias can remain after forward convergence. We also provide lapanda-KKT, which differentiates the original KKT conditions without this additional approximation.
Such regularity assumptions are commonly required by nonconvex differentiable solvers to establish local differentiability of the optimizer mapping and justify sensitivity computation.
W2. The rectangular-obstacle formulation violates LICQ.
We introduced this problem to examine lapanda’s empirical performance outside the assumptions of our theory. Degenerate MPCCs are not the main problem class targeted by lapanda. We have clarified the purpose of this experiment and also report results for a smoothed rectangular-obstacle formulation.
W3. Convergence criteria.
Thank you for raising this valuable question. We had not discussed the relationship between stopping criteria and sensitivity accuracy in sufficient detail. Appendix B.6 now analyzes three sources of sensitivity error: forward-point error, numerical backward-solve error, and the finite-penalty bias of lapanda-ALM. Based on this analysis, we have revised the learning comparison to evaluate the computation required to reach the same loss target; see Q3.
W4. Contributions of the individual components.
The core of our work is the identification and exploitation of different problem structures in the backward pass. We analyze the relationship between original-problem and ALM-subproblem sensitivities and develop two matrix-free backward strategies with different accuracy–efficiency characteristics.
For the forward pass, our contribution is primarily the analysis establishing the applicability of PANDA to the ALM subproblems and the local convergence of the resulting method. The PANDA/PANOC ablation is reported under Q1.
Q1. Ablations with alternative inner solvers.
We compare PANDA and PANOC within the same lapanda ALM implementation. Appendix C.4.2 reports the following results; each cell gives mean forward time in milliseconds / total inner iterations.
Each setting contains 18 sampled training inputs. The gains are largest on Robot arm, where adaptive step-size enlargement substantially reduces the number of inner iterations. The differences are smaller on CartPole and Quadrotor.
Q2. Sensitivity to penalties, tolerances and conditioning.
Thank you for this valuable question. Appendix C.4.1 adds a controlled quadratic problem with analytical reference gradients to examine these factors separately.
At the exact forward solution, using exact backward solves:
Increasing ρ reduces the bias, but the required penalty depends strongly on conditioning. In the last row, the subproblem condition number increases to approximately 107.
For an ill-conditioned instance with δ=μ=10−4 and ρ=103, tightening the backward tolerance gives:
The 10−9 MINRES runs did not meet the requested residual target.
The CG subproblem-solve error is measured against its exact subproblem gradient. Tightening the tolerance reduces this error, while the total error remains limited by finite-penalty bias.
Finally, with the same forward KKT residual 10−3 and exact backward solves:
These results show how conditioning amplifies sensitivity errors and why tightening only one tolerance may be insufficient. We have added this observation to the limitations.