- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This work investigates the deconfounding problem in high-dimensional causal inference and proposes Spec-LBI, which integrates Trim-based spectral deconfounding with linearized Bregman iteration (LBI). Theoretically, it establishes that the Trim transformation can asymptotically restore the irrepresentable condition, extending LBI's selection and estimation consistency guarantees to random-design settings with latent confounding. The method is evaluated through simulations and two real-world applications.
Critical strengths
- The paper addresses the spectral confounding problem and proves that Trim-based spectral preprocessing can make the irrepresentable (IRR) condition hold asymptotically.
- The paper extends the existing statistical theory of linearized Bregman iteration (LBI). While the theoretical guarantees of the original LBI are established under fixed-design assumptions without latent confounding, this work extends feature selection consistency and -estimation consistency to random-design settings with latent confounding, establishing a convergence rate for the proposed Spec-LBI estimator.
Critical weaknesses
- In Section 4.1, the intuitive statement “Intuitively, the IRR condition requires that causal features are weakly correlated with others” is conceptually problematic. The irrepresentable (IRR) condition is purely a design‑matrix‑level assumption for sparse regression, where the set S denotes the active set of non‑zero regression coefficients rather than true causal features. By directly equating regression‑level active features to causal features in this intuitive explanation, the paper implicitly assumes that non‑zero regression coefficients correspond exactly to true causal variables, which conflates correlational regression quantities with causal quantities without explicit justification.
- Spec‑LBI acts solely as an estimation solver and provides no causal identification guarantees. However, the manuscript does not clearly articulate under which exact set of assumptions causal quantities become identifiable within the proposed pipeline. This exposition creates potential risk of misinterpretation, where readers may mistakenly treat Spec‑LBI as a general‑purpose tool for discovering causal features directly from confounded observational data, rather than an estimator operating conditional on pre‑established causal identifiability.
Questions for authors
-
As an iterative algorithm, the proposed method lacks sufficient algorithmic discussion in the method section. The manuscript does not clarify whether the iterative sequence is guaranteed to converge, what fixed‑point solution it converges to, practical rules for stopping criteria such as coefficient change threshold or maximum iteration number, whether multiple local solutions exist, and whether initialization choices can alter the final selected feature set. These practical implementation details are critical for reproducibility and real‑world deployment, yet they remain underexamined.
-
When deployed for causal backdoor adjustment, one needs to select confounders satisfying the backdoor criterion, instead of merely selecting variables predictive of outcome Y. Spec‑LBI and Lasso are optimised for predictive performance. Predictive variables do not necessarily qualify as valid confounders; they could be colliders (descendants of the outcome variable Y). Without additional constraints, Spec‑LBI may select such collider variables into the adjustment set and introduce collider bias that invalidates causal estimation. This important risk of using prediction‑oriented sparse regression for confounder selection is not acknowledged in the method section.
-
The presented theory hinges on multiple stringent asymptotic assumptions, including the beta‑min condition, prescribed sparsity level of , and specific scaling requirements for the Trim transformation parameters. None of these assumptions can be empirically verified given real‑world observational datasets. The manuscript lacks systematic discussion regarding performance degradation when these assumptions are violated in practice.
-
The practical performance of Spec‑LBI heavily depends on critical hyper‑parameters: damping factor , step‑size, and early‑stopping time . While cross‑validation is suggested as a practical recipe for hyper‑parameter tuning, the paper provides no sensitivity analysis for these hyper‑parameters. Consequently, it remains unclear how hyper‑parameter misspecification in finite samples would harm feature‑selection consistency and estimation error.
-
This work falls into the family of spectral‑deconfounding methods built on the dense‑confounding factor‑model framework. Although it cites prior Trim‑based spectral deconfounding literature, the paper lacks systematic conceptual positioning and empirical benchmarking against closely‑related competing approaches for high‑dimensional latent confounding causal inference.
5 comments
Contributions
2.Contributions
We thank the reviewer for raising these concerns. Here, our main claim is that both our experimental design and algorithm are aligned with our two main contributions built upon the dense-confounding setting: (1) explaining theoretically how spectral deconfounding improves variable selection and (2) building on this insight to propose Spec-LBI for bias reduction and more accurate estimation. Below, we address the related concerns.
Questions 5: About contribution and related work.
Response: We thank the reviewer for raising this concern. We would like to clarify that the comparisons conducted in our experiments are sufficient to support our claims and contributions. Specifically, as stated in Lines 65 and 76 of the manuscript, our work has two main contributions. First, we provide a theoretical understanding of why spectral deconfounding can improve estimation. Second, we propose the Spec-LBI estimator as a bias-reduction approach to Lasso, aiming to substantially reduce estimation bias and improve estimation accuracy.
Regarding the first contribution, our goal is to understand the underlying mechanism of spectral deconfounding rather than to propose a new method. Specifically, we theoretically establish that spectral deconfounding can drive the irrepresentable (IRR) condition toward zero, and further validate this theoretical finding through numerical experiments. Regarding the second contribution, we demonstrate that the proposed Spec-LBI estimator can substantially reduce the bias of Lasso and thereby improve estimation precision.
Questions 1: About the the coverage of Spec-LBI iterations.
Response: We thank the reviewers for raising this question. We would like to clarify that the Spec-LBI iterations are used to select variables by early stopping, rather than to solve the associated optimization problem to convergence. The key is therefore to choose an appropriate early stopping time. We have provided the theoretical stopping time in lines 1207–1211 (1261–1265 in the revised version), while in practice we use cross-validation following Osher et al. (2016)[8], as described in lines 319–321 ( lines 323–329 in the revised version). For initialization, we follow Osher et al. (2016)[8] and set , as specified in lines 188–191 (196–199 in the revised version). Furthermore, LBI indeed converges to the unique solution of its associated constrained optimization problem established in [9].
Others
3. Others
Here, we discuss some commonly used assumptions underlying our theoretical results and Spec-LBI’s sensitivity to hyperparameter choices.
Questions 3: About asymptotic assumptions in real world.
Response: We thank the reviewer for raising this concern. We would like to emphasize that the beta-min condition and the sparsity formulation are standard and foundamental in the high-dimension statistics [2-4]. In particular, the sparsity constraint is to ensure that the true coefficient is identifiable (even without the latent confounder) in high dimensional setting. For the beta-min condition, even without this condition, we can also achieve the convergence rate of
For the trim parameter , Theorem 4.1 remains valid over a broad range of values of the scaling parameter. Roughly speaking, can be chosen flexibly above the number of latent factors, as long as it satisfies . For example, for fixed ,we can choose .
Furthermore, we conducted additional experiments to demonstrate the robustness of our method when these assumptions are violated. For the sparsity constraint, we vary the sparsity level. Figures 10 (b)-(c) show that the -error scales approximately as with the sparsity level , while remaining nearly unchanged as the trim parameter increases.
For beta-min, we vary the coefficient magnitude from to and report the estimation error. As shown, our method achieves a lower -error than all baselines, even when the beta-min condition is violated ().
| Method | δ | ℓ₂ error ↓ |
|---|---|---|
| Lasso | 1.00 | 2.034 |
| Trim+Lasso | 1.00 | 0.590 |
| Ours | 1.00 | 0.149 |
| Ours | 0.50 | 0.177 |
| Ours | 0.20 | 0.312 |
| Ours | 0.05 | 0.137 |
Questions 4: About hyperparameters.
Response: We thank the reviewer for this question. We would like to clarify that we have already discussed the hyperparameters and how their values affect the model in lines 315–321 (lines 323–329 in the revised version). To verify these claims empirically, we have also conducted additional experiments. Let and denote the true and estimated supports, respectively. We report the F1 score, , and for support recovery and the -error for estimation accuracy, all averaged over 20 repetitions:
The damping parameter , the step size : Since these parameters must jointly satisfy the condition , we evaluate their effects jointly. To show these effects more clearly, we use a larger support size of . The results show that a larger increases the path time but can reduce the estimation error.
| Step size | F1 ↑ | FP ↓ | FN ↓ | ℓ₂ error ↓ | Path time (s) ↓ | |
|---|---|---|---|---|---|---|
| 2 | 0.64±0.12 | 18.60±9.38 | 0.00±0.00 | 0.57±0.14 | 0.05±0.01 | |
| 10 | 0.95±0.04 | 1.55±1.32 | 0.00±0.00 | 0.31±0.06 | 0.21±0.04 | |
| 20 | 0.96±0.03 | 1.15±1.09 | 0.00±0.00 | 0.30±0.06 | 0.42±0.06 | |
| 50 | 0.98±0.02 | 0.65±0.67 | 0.00±0.00 | 0.29±0.06 | 1.02±0.14 |
The stopping time: We vary the stopping time relative to the cross-validated choice to assess sensitivity. The results show that stopping too early misses true variables and increases the estimation error.
| Stopping time | F1 ↑ | FP ↓ | FN ↓ | ℓ₂ error ↓ |
|---|---|---|---|---|
| 1.00±0.00 | 0.00±0.00 | 0.00±0.00 | 0.15±0.04 | |
| 0.19±0.34 | 0.00±0.00 | 4.20±1.58 | 1.95±0.64 | |
| 0.95±0.13 | 0.85±2.13 | 0.00±0.00 | 0.19±0.12 |
Causal interpretation and identification
We thank the reviewer for the helpful feedback and thoughtful questions. We address the questions below in three parts, including causal interpretation and identification, contributions, and others.
1.Causal interpretation and identification
We sincerely thank the reviewer for raising these concerns. Here, our main claim is that the identifiability relies on the widely used dense-confounding assumption, and our causal interpretation is based on the structural equation model (SEM) formulation of model (1) in Line 138 (Line 144 in the revised version). Below, we address the related concerns.
Weakness 1 :About the causal interpretation of non‑zero regression coefficients and IRR condition.
Response: We thank the reviewer for pointing out this concern. We would like to claim that our causal interpretation of the nonzero regression coefficients follows from the structural equation model (SEM) formulation of model (1), as discussed in the spectral deconfounding literature [1, 5]. Specifically, under this SEM formulation of the linear model, it can be easily shown that each nonzero coefficient in βi∗ indeed represents the causal effect of Xi on the response Y. That means, under the SEM formulation of model (1), those active features with nonzero regression coefficients are exactly causal features. Consequently, the active features with nonzero regression coefficients correspond precisely to the causal features. In this sense, the irrepresentable (IRR) condition is imposed on the design matrix with respect to the set of causal features. We have incorporated these explainations into the revised manuscript (Lines 140–159 and 255–256).
Weakness 2 :About the causal identification guarantees.
Response: We thank the reviewer for pointing this out. We would like to clarify that our estimation result relies on the dense confounding assumption, as we have already stated on lines 160-172 ( lines 168-179 in the revised version). The dense confounding assumption has been widely adopted to ensure the identifiability of the causal effect [1,5,6,7]. On the basis of this assumption, we show that Spec-LBI can mitigate confounding bias while reducing the shrinkage bias relative to existing spectral deconfounding methods, and even achieve the oracle minimax estimation rate.
Questions 2: About the backdoor adjustment.
Response: We thank the reviewer for raising this concern. We would like to clarify that Spec-LBI actually does not use backdoor adjustment for causal estimation under the structural equation model (SEM) formulation of model (1). Instead, our debiasing approach builds on the dense confounding assumption, under which latent confounders induce a few spiked singular values in the covariate matrix. Under this assumption, spectral deconfunding shrinks these singular values and consequently removes the confound effect.