- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes PV-Surgery, a training method for multivariate time-series forecasting. It estimates variable-wise gradients in a single backward pass, selects layers, conditionally groups gradients, corrects their directions, and restores the norms of the surgery inputs. The paper also distinguishes gradient conflict from actual performance degradation under shared training. Across five backbones, seven datasets, and four forecasting horizons, it reports average relative reductions of 3.61% in MSE and 2.93% in MAE compared with standard MSE training.
Critical strengths
The paper goes beyond reporting negative gradient cosines by comparing shared training with full-input single-target models and examining different partner compositions. These diagnostics provide useful evidence that conflict frequency alone is insufficient to determine whether sharing helps or hurts prediction. This meaningfully advances understanding of variable-wise optimization in forecasting.
The method is evaluated across 140 backbone–dataset–horizon settings, with additional baselines and component ablations. The paper also directly compares gradient proxies with exact per-variable gradients, providing useful evidence about proxy quality beyond forecasting performance alone. These experiments help assess the method’s effectiveness and limitations across the evaluated settings.
Critical weaknesses
Equation 6 checks whether the variable-wise proxies sum to the reference gradient. However, individual proxy errors can cancel, producing an accurate sum despite inaccurate variable-wise estimates. Figure 5 and Appendix J provide useful evidence of higher fidelity after layer selection, but selection also depends on output-layer inclusion and gradient norms. It therefore remains unclear whether the reconstruction-error score itself helps identify more accurate proxies.
Beyond directional correction, the method replaces gradients with proxy sums and sets current data gradients to zero on unsupported hooked blocks. The output-cache ablation removes several components together, so it does not separate these effects from directional correction. Appendix I provides a useful comparison using the same proxy construction, layer-selection rules, and gradient assembly, but pooling, candidate selection, and aggregation scale also differ across methods. Moreover, the main results and ablations use only seed 42, and the gradient-method comparison is limited to MICN. These limitations make it difficult to assess the additional gains and smaller ablation differences with confidence.
Questions for authors
With complete and consistently partitioned linear-layer caches, Equation 4 appears to recover the summed reference gradient despite downstream variable mixing. What causes nonzero reconstruction error on supported layers in practice? Does this error predict per-variable proxy fidelity beyond output-layer inclusion and gradient-norm-based selection?
Can you provide a control that keeps proxy construction and gradient assembly unchanged while turning off directional correction, i.e., setting ? How often does the assembly rule materially change unselected gradients or zero otherwise nonzero reference gradients? Does the output-cache ablation retain sum-loss training?
Can you provide paired multi-seed results for PV-Surgery, standard MSE training, MGDA, and GradVac on representative MICN settings? These would help assess whether the additional improvements and small ablation differences are consistent across runs.