- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Convex-SKM-Net is a differentiable feasibility-repair layer for affine equality and convex inequality constraints. It enforces equalities, constructs linearization halfspaces, and approximately solves minimum-displacement block subproblems using fixed-depth dual projected-gradient updates. A learned positive-definite mobility adapts the correction geometry. The paper establishes convergence under suitable assumptions and evaluates the method on control, power-system convex relaxations, and optimization benchmarks.
Critical strengths
-
Practical generality: The method requires constraint residuals and subgradients rather than constraint-specific inequality projectors. Block updates and reused linearizations support efficient GPU execution.
-
Relevant theoretical analysis: The finite-inner-depth progress bounds address an important tradeoff between correction accuracy and inference cost.
-
Substantial empirical evaluation: Experiments report objective quality, original-constraint feasibility, and latency, with useful baseline sweeps, matched-prediction comparisons, and mobility ablations.
Critical weaknesses
-
The incremental novelty needs clearer justification. Differentiable prediction-and-repair frameworks already exist in DC3, while halfspace approximations and block subgradient projections are established convex-feasibility techniques. GLinSAT also provides a differentiable, matrix-factorization-free constraint layer using dual first-order optimization. The paper should more precisely identify what is new beyond extending these ideas to nonlinear convex constraints and learning the correction geometry.
-
In particular, one zero-initialized dual step gives , which equals one gradient step on the local squared-violation objective. This does not make the complete methods equivalent, but motivates isolating the benefits of multiple dual steps and the other design choices.
-
Important inference configurations fall outside the stated guarantees. Appendix B acknowledges that the one-step power estimates used in ACOPF and QCQP inference may violate the theoretical step-size condition. A matched comparison with a certified safe rule is needed to establish the performance cost of retaining the convergence guarantees.
-
The source of the performance gains is not fully isolated. In matched synthetic ablations, dual PGD is only approximately 1.06–1.17 times faster than Violation-GD. Additional comparisons of correction distance, downstream objective quality, and robustness would clarify its specific advantage. GLinSAT is cited but not evaluated; comparison on a bounded, linearly constrained benchmark would be useful.
-
Some empirical claims need stronger support. Traditional solvers and neural methods use different hardware, and SOC-MPC solver evaluations do not use warm starts. QCQP uses only one training seed; repeated timing passes do not establish training robustness.
Questions for authors
-
How do latency, feasibility, and objective quality change with theoretically safe inference step sizes?
-
What specifically distinguishes the finite-depth analysis from existing inexact block-projection results?
-
Can the authors add GLinSAT and matched violation-gradient repair with learned preconditioning as baselines?
Responses to Reviewer NHX2
Thank you for the detailed review and for noting the generality of the oracle interface and the relevance of the finite-depth bounds.
Safe inference steps (Q1). We held each checkpoint fixed and replaced power1 with ω/ℓB, where ℓB bounds the maximum absolute Gram row sum for the mobility-transformed, normalized rows. We used ω=1.8 on QCQP and 1.95 on ACOPF. Both rules met tolerance on every input in these comparisons. For dual PGD on QCQP (seed 456, 10−8), power1 averaged 3.026 ms (0.01155% gap) and Gershgorin 1.8 averaged 3.826 ms (0.01213%), excluding transfers. On SOCP300, both step rules met 10−3 on all 1,000 inputs for each seed. We clipped negative per-input gaps to zero before averaging.
The safe rule was slightly faster on the 57-bus tasks. We will tabulate mean and P99 latency for all tasks.
Finite-depth analysis (Q2). Our bounds apply after a fixed T even if a block inequality remains violated. We retain T-SKM-Net's equality projection. Residuals and subgradients define a block of halfspaces, and we take T dual PGD steps on its minimum-displacement QP. Kiwiel (1995) aggregates inequalities into a surrogate halfspace. Necoara and Nedić (2021) analyze minibatch subgradient corrections. DC3 takes gradient steps on constraint violation, and GLinSAT uses an entropy-regularized formulation for bounded linear constraints. Díaz Millán et al. (2021) stop an inner solver at a feasible approximate projection using an error test.
With zero initialization and step size 1/LB, Thm. 4.1 guarantees a decrease of at least cB,T>0 in squared distance to every feasible point whenever the block is violated, for any T≥1. The first top-b block captures at least b/m of the total squared normalized violation. Under the assumptions of Cor. 4.2 this gives outer convergence, with a linear distance rate under Slater's condition. In the analysis coordinates, Eq. (24) bounds the squared error relative to the fixed block's exact displacement Δ⋆ by χB∥Δ⋆∥2/(T+χB), where χB depends on that block. As you note, with the same rows and step size the first dual step from zero equals a squared-violation gradient step. At T=1 the measured mean gaps agree to roundoff.
Matched VGD and GLinSAT comparisons (Q3). On QCQP (seed 456), we jointly trained one model per update and used its training update at test time. Both met 10−8 on all 833 inputs. In the same RTX 4090 run as Q1, dual PGD (power1) averaged 3.026 ms (0.01155% gap) and VGD (power1) 3.448 ms (0.01543% gap). When trained separately on the affine task, dual PGD and learned-preconditioned VGD gave five-seed mean gaps of 0.159% and 0.172%, respectively.
In 96 QCQP post-processing comparisons (four predictors, four tolerances, two step rules, T = 5, 10, or 20), both repairs passed all 833 inputs. Relative to VGD, dual PGD reduced mean latency by 3.37–11.60% and mean displacement by 0.0011–0.0096%. Mean signed gap fell by 0.000686–0.003474 percentage points. From matched starts in nine affine stress settings, dual PGD reached 10−3 within 100 outer iterations on 461/576 cases (80.0%) and VGD on 384/576 (66.7%).
On a bounded linear task (16 variables, five seeds), we used the authors' GLinSAT implementation. All three methods ran on the same TorchAX/XLA stack on RTX 4090s and met 10−3 on all 64 test inputs in each seed.
Solver timing, warm starts and seeds. Neural methods ran on RTX 4090 GPUs. SOC-MPC solvers used one CPU thread. ACOPF used MOSEK's default threading (App. D.5). The original SOC-MPC contexts were independent. At H=80, a reference controller generated common trajectories for three initial deviations and two feasibility tolerances (10−3,10−6). For COSMO, we set both
eps_absandeps_relto 10−5 in the looser test and 10−8 in the tighter one. It reused its workspace and the previous primal and dual states. Timing excludes the first step of each trajectory and includes transfers for the GPU method. All methods met the external tolerance in all six settings. At 10−3 and the smallest deviation, warm starting reduced COSMO's mean latency from 25.5 to 4.00 ms, versus 4.48 ms for our model. Our model was faster in the other five settings. Its mean absolute relative objective error was 0.73–0.97%. We will report both methods' objective errors in the full table.Four additional QCQP training seeds bring the total to five. Each passed all 833 inputs at 10−6. The gap (mean ± sample SD across seeds) was 0.0122% ± 0.0014% with power1 and 0.0118% ± 0.0003% with the safe rule.
We hope these results address your concerns.