- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
SETSUNET proposes a shared learned optimizer for few-step inverse problems. It first computes a numerical base update in a measured subspace, then uses a small graph network to generate complementary search directions from gradient and curvature information. These learned directions are projected to preserve the base solution’s stationarity and are combined using a two-view minimax consensus rule. The same checkpoint is evaluated across geometric, restoration, stereo, and graph optimization tasks. The paper also establishes whitening equivariance, allowing equivalent Cholesky whitening without retraining.
Critical strengths
- This design features a clear mechanism.
- The learnable modules are well integrated with the analysis solver.
Critical weaknesses
In visual tasks, the contribution of the learned direction has not yet been fully isolated. A controlled ablation study is needed: remove the learned completion information while retaining the remaining solver components.
Having the same number of outer iterations does not guarantee comparable computational costs. Under the same Jacobian budget, some rankings may change, indicating that the advantage depends on how the budget is defined.
Questions for authors
In the whole-block 3D temporal experiment, the theoretical value for learning the completion term is zero; however, on major visual benchmarks, how often does it produce a non-zero correction? How much does performance decline when it is disabled?
Why does the gain of minimax depend on CG refinement when the bias is stronger, while the mean coordination method actually performs better under asymmetric noise? How should coordination rules be selected in practical applications?
2 comments
I thank the authors for the clarifications and additional experiments. The response addresses my specific questions and strengthens the empirical support. However, the additional evidence does not substantially change my assessment of the paper’s overall contribution and informativeness. I therefore maintain my original rating. I have no further questions.
Response to jJxX
Thanks for asking for strictly matched ablations and equal-budget comparisons; we ran both directly to isolate each factor.
W1, Q1: In Sec. 4.4 and Table R1, we added a 120-case matched ablation that disables only learned completion while keeping the base step, configured CG, finite-step rule, initialization, 5-step budget, and shared checkpoint untouched. Counting states where the pre-CG completion-to-base norm ratio exceeds 10−10, completion is active in 120/120 (multiframe), 160/160 (biased graph), 160/160 (noisy graph), and 159/160 (SE(3)) states, cutting mean error by 2.44%, 20.70%, 48.84%, and 6.66%. For visual edge cases (Appendix H, Table R4, Fig. 6), full-block stereo without spectral clipping (H=I, d0=−g) and 8-DOF pairwise HPatches (full-rank base) are structural zero-completion boundaries; in small restoration controls, completion activates in 59/60 states with nearly unchanged mean PSNR (Table R4), while general multiblock gains are isolated in Table R1.
W2: Sec. 4.3, Appendix I, and Fig. 8 report head-to-head comparisons under a matched 21-joint-Jacobian (21J) budget. Under 21J, SETSUNET stays best or practically tied (within 2%) on Low light, Stereo, SE(3), and Blur; over Ceres, it gains 1.873 dB in low-light PSNR and cuts stereo and biased-graph error by 5.83% and 4.21%. Note that in biased graph, the Jacobian is a preconstructed constant A, yet counting both per-step references caps us at 10 steps / 20J versus HSLM's 21 steps / 21J, highlighting how derivative-request counts can diverge from actual compute work.
Q2: In Sec. 4.5, Fig. 5, and Appendix G, we crossed minimax/mean with CG2/CG0 using the same checkpoint. Under shared curvature, minimax penalizes view disagreement while CG2 cleans up the remaining mean-model residual: at the two stronger bias levels, minimax+CG2 beats mean+CG2 by 14.36% and 12.08%, whereas without CG the differences are −3.23% and −0.72%. Because asymmetric random noise also creates view disagreement without systematic bias, mean is better there. In practice, one can fix the rule upfront from the measurement model and validation data; across all main benchmarks, we never switch per case and keep minimax fixed.