- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper wants each person’s treatment effect from panel data (n people × m time points) with random, unknown treatment probabilities. It frames this as matrix completion and claims a simple, fast estimator with per-person error of about √(1/n + n/m²), plus a new row-wise perturbation bound. In experiments the estimator beats Horvitz–Thompson and Hájek estimators.
Critical strengths
Theoretically solid.
Critical weaknesses
-
Most components of the analysis are standard: inverse-propensity rescaling, matrix Bernstein, Weyl, symmetric dilation, gap-based rank selection, and the contour expansion of Tran & Vu. The genuinely new ingredient appears to be Theorem 4.2. However, the paper does not explain precisely what it improves over (i) existing ‖·‖_{2→∞} subspace bounds (Cape et al. 2019; Abbe et al. 2020) converted to low-rank-approximation bounds, and (ii) √m times the entrywise bound of Tran & Vu (2025a). Please state explicitly which factor is gained (e.g., condition number, gap at the true rank, logarithmic factors) and give an example where Theorem 4.2 is strictly better. Without this comparison, the technical contribution is hard to assess.
-
The main comparison is to Athey et al. (2021) and Agarwal et al. (2023), which study harder assignment designs (block adoption and missing-not-at-random). Under the independent Bernoulli design considered here, existing entrywise guarantees for spectral matrix completion (e.g., Abbe et al. 2020; Chen et al. 2019) appear to already imply row-wise bounds in the row-homogeneous case. The authors should clarify what their results add beyond this literature. The contribution then appears to rest on the new ‖·‖_{2,∞} perturbation bound and the treatment of nonuniform propensities, and the latter yields vanishing error only for noise-like nonuniformity.
-
The paper gives an error bound with unknown constants, not uncertainty estimates. A practitioner can’t say “Ana’s effect is 0.5 ± 0.2.” For individual effects, inference matters as much as the point estimate.
Questions for authors
See above
5 comments
Response to Reviewer RJqk (2/3)
Weakness 2: “The main comparison is to Athey et al. (2021) and Agarwal et al. (2023), which study harder assignment designs (block adoption and missing-not-at-random). Under the independent Bernoulli design considered here, existing entrywise guarantees for spectral matrix completion (e.g., Abbe et al. 2020; Chen et al. 2019) appear to already imply row-wise bounds in the row-homogeneous case. The authors should clarify what their results add beyond this literature. The contribution then appears to rest on the new perturbation bound and the treatment of nonuniform propensities, and the latter yields vanishing error only for noise-like nonuniformity.”
We agree that when all entries share a common observation probability and the condition number is bounded, existing entrywise guarantees imply row-wise bounds, and we will discuss them explicitly. Our results go beyond this setting in three ways.
-
Unit-specific rates. Abbe et al. (2020) and Chen et al. (2019) assume a common observation probability. Our row-homogeneous designs allow each unit its own unknown treatment rate, as in stratified randomization.
-
Condition number. These results assume a bounded condition number or depend on it polynomially, while our bound does not depend on it. This matters, for example, when a strong common trend dominates weaker unit-specific patterns. In the example in our answer to Weakness 1, our bound vanishes while that of Abbe et al. grows with the dimension.
-
Nonuniform designs. With the factor identified by Reviewer rWGs corrected, our guarantee covers designs whose propensities vary within rows with bounded , such as schedules in which each unit's treatment probability is raised at a bounded number of times, with a bounded number of units raised at each time. Designs whose propensities vary over time in the same way for all units, such as ramp-ups, are covered by a column-scaled variant of our estimator (see our response to Reviewer fC3x).
We will also clarify that Athey et al. (2021) and Agarwal et al. (2023) study different assignment models.
Weakness 3: “The paper gives an error bound with unknown constants, not uncertainty estimates. A practitioner can't say `Ana's effect is .' For individual effects, inference matters as much as the point estimate.”
We agree that uncertainty quantification for individual effects is important. Our results concern point estimation. Explicit constants, together with estimates of the parameters in our bound, would give error bars, but these would be conservative, since the bound holds simultaneously for all units. Calibrated intervals require a distributional approximation for each estimated effect that accounts for the bias from truncation and the data-driven choice of rank, as developed for matrix completion under uniform sampling by Chen, Fan, Ma, and Yan (2019). Tightening our constants and developing such inference for our estimator are important directions but beyond the scope of this work. We will discuss them in the paper.
Response to Reviewer RJqk (3/3): Technical follow-up
Technical follow-up to Reviewer RJqk
This follow-up gives the calculations behind our answer to Weakness 1.
(i) Converting subspace bounds. Let and be the projections onto the top- left singular spaces of and . Since and , A two-to-infinity bound on singular subspaces, such as Cape, Tang, and Priebe (2019), Theorem 3.7, controls , and the identity multiplies this error by . Combined with the Davis–Kahan bound for the operator-norm part, this conversion yields a bound with factors and , where Theorem 4.2 has . The example in (iii) shows that this dependence appears in the published reconstruction bound of Abbe et al. (2020).
(ii) Comparison with Tran and Vu (2025a). Let , and let be the standard coherence. Their Theorem 2.1 (arXiv v2) assumes and gives
\leq C\\,\frac{(\log N+\mu_0)\log^2N}{\sqrt{mn}}\\,r\sigma_s \left(\frac K{\sigma_s}\sqrt{\frac Np}+\frac{rK\sqrt{\log N}}{\delta_s\sqrt p}+\frac{r^2\mu_0K\log N}{p\\,\delta_s\sqrt{mn}}\right).$$ For $m=n=d$ and bounded $r$, $\mu_0$, $K$, $p$, and $\sigma_s/\delta_s$, the first term dominates, and $\sqrt d$ times the bound is of order $\log^3d$. For the same noise, Theorem 4.2 gives $\\|\widetilde A_s-A_s\\|_{2,\infty}=O(\sqrt r\mu\log^2d\\,\sigma_s/\delta_s)$. Our incoherence parameter satisfies $\mu=\sqrt{r\mu_0}$, so $\sqrt r\mu=r\sqrt{\mu_0}$, and the two bounds have the same dependence on the rank. Their Theorem 2.1 does not apply to mixed noise $E=E_R+E_0$. Their general deterministic result (Theorem 3.2) has different hypotheses, so we compare only with Theorem 2.1. *(iii) The rank-two example.* Let $d$ be even, let $u=d^{-1/2}\mathbf 1$, let $v$ have $d/2$ entries equal to $d^{-1/2}$ and $d/2$ entries equal to $-d^{-1/2}$, and set $$A=\frac d4uu^\top+\frac{d^{4/5}}4vv^\top\\,.$$ Then $A$ has rank two, entries bounded by $1/2$, incoherence parameter $\mu=\sqrt2$, and condition number $\kappa=d^{1/5}$. Observe each entry independently with probability $p=1/2$, without added noise, and let $\widetilde A=2D\odot A$. Then $E=\widetilde A-A$ has independent, centered entries bounded by $1/2$, so $\\|E\\|_{\mathrm{op}}=O(\sqrt d)$ with high probability. The gap $\delta_2=\sigma_2=d^{4/5}/4$ exceeds $6\\|E\\|_{\mathrm{op}}$ for large $d$, and $\sigma_2/\delta_2=1$, so Theorem 4.2 gives $$\frac{\\|\widetilde A_2-A\\|_{2,\infty}}{\sqrt d}=O\left(\frac{\log^2d}{\sqrt d}\right).$$ [Abbe, Fan, Wang, and Zhong (2020), Theorem 3.4](https://pmc.ncbi.nlm.nih.gov/articles/PMC8046180/), bounds the entrywise reconstruction error by $C\eta^2\kappa^4(\\|A\\|_{\max}+\sigma)\sqrt{N\log N/p}$, where $\eta$ is the largest row norm of the singular vector matrices and $\sigma$ is the noise level. Here $\eta^2=2/d$, $N=2d$, and $\sigma=0$, and the signal condition of the theorem holds because its left-hand side is $O(d^{-1/10}\sqrt{\log d})$. The bound is of order $d^{3/10}\sqrt{\log d}$. Since $\\|F\\|_{2,\infty}/\sqrt d\leq\\|F\\|_{\max}$ for every $d\times d$ matrix $F$, it gives a normalized row error bound of the same order, which grows with $d$.
Response to Reviewer RJqk (1/3)
Thank you for identifying the comparisons that would make the contribution clearer. We agree that Theorem 4.2 is the main new technical result.
Weakness 1: “Most components of the analysis are standard: inverse-propensity rescaling, matrix Bernstein, Weyl, symmetric dilation, gap-based rank selection, and the contour expansion of Tran & Vu. The genuinely new ingredient appears to be Theorem 4.2. However, the paper does not explain precisely what it improves over (i) existing ∣⋅∣2→∞ subspace bounds (Cape et al. 2019; Abbe et al. 2020) converted to low-rank-approximation bounds, and (ii) m times the entrywise bound of Tran & Vu (2025a). Please state explicitly which factor is gained (e.g., condition number, gap at the true rank, logarithmic factors) and give an example where Theorem 4.2 is strictly better. Without this comparison, the technical contribution is hard to assess.”
We answer the three parts of this question in turn. The technical follow-up below gives the calculations.
(i) Subspace bounds. Converting a bound on singular subspaces into a bound on the low-rank approximation multiplies the subspace error by σ1(A), so the converted bound depends on the condition number κ=σ1/σs. For example, the reconstruction bound of Abbe et al. (2020, Theorem 3.4) has a factor κ4 and a signal condition at the true rank. Theorem 4.2 bounds the low-rank approximation directly. It has no condition-number factor and needs a gap only at the retained rank.
(ii) Tran and Vu (2025a). Our proof adapts their contour expansion. For random noise, their Theorem 2.1 requires the gap δs≥40rK(m+n)/p, which grows linearly with the rank, while Theorem 4.2 requires δs≥6∣E∣op. When the rank, the incoherence, and σs/δs are bounded, m times their entrywise bound is of order log3(m+n), while our row-wise bound is of order log2(m+n). Theorem 4.2 also allows a deterministic perturbation in addition to the random one, which our analysis of nonuniform designs needs. The factors gained are therefore the factor r in the gap condition and one logarithmic factor. For a perturbation with both parts, ER+E0, their Theorem 2.1 does not apply, and bounding the row-wise error by the operator norm, using the spectral bound of Tran, Vishnoi, and Vu (2025), loses a factor of order m+n on the random part, up to logarithmic factors, whereas Theorem 4.2 keeps the random-noise rate.
(iii) An example. Consider an incoherent rank-two d×d matrix with entries bounded by 1/2 and singular values d/4 and d4/5/4, so that κ=d1/5, observed independently with probability 1/2 and without added noise. Theorem 4.2 bounds the normalized row error by O(log2d/d), which vanishes. The reconstruction bound of Abbe et al. (2020, Theorem 3.4) is of order d3/10logd, which grows with d, even though its signal condition holds.
We will add these comparisons and the example to the paper.