- Rating
- 1
- Confidence
- 1
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 3
Read review
Paper summary
The paper compares policies through the population laws of individual outcome distributions. It studies the sharp range of cross-person matching costs and constructs globally feasible dual certificates with simultaneous coverage. For exactly observed distributions and fixed finite covariate/action sets, it establishes logarithmic minimax rates for both endpoints when local and global cost orders match. It also studies structured outer laws, estimated propensities, and finite within-person samples.
Critical strengths
-
The minimax lower bounds apply to every estimator of either scalar endpoint, extending previous results on slow empirical transport convergence. Matching upper bounds and the persistence of the barrier under uniformly bi-Lipschitz individual quantiles provide a useful account of what makes these comparisons difficult.
-
The certificates handle global feasibility, directional discretization errors, and policy search. The paper credits the inherited feasible-dual principle and adds calibrated finite-cell AIPW and finite-bag corrections. Controlled comparisons separate learning, extension, and calibration errors, supporting the distinction between valid certificates and informative ones.
Critical weaknesses
- The writing of current draft need serious polish. I can barely comprehend the introduction due to lack of transition words or coherence. The figures appear to be directly generated by AI and are difficult to understand. The current draft is not appropriate for publishing.
- Statistical attainability does not establish affordable computation. Completed anchor sets can grow exponentially in inverse precision (E.5), while general convex transforms may require certified global optimization (E.6). K.3.6 demonstrates improved quadratic extensions, but leaves runtime scaling unclear. The main text should distinguish tractable costs from the general construction.
- The small calibration-to-learning-gap ratio emphasized in Figure 3a can coexist with wide certificates. At total n=65536, the equal-budget quadratic experiment retains 36.1% of the lower endpoint (Table 30); the unknown-propensity experiment has lower/upper ratios of 0.786/1.572 (Table 3). These are different designs, but both show why the main discussion should include endpoint-normalized precision alongside calibration overhead.
- The main text is dense and relies heavily on appendix references. It states the finite-design restrictions, but the connection between the geometric conditions and the rates is difficult to follow. A short sketch linking the hard codes and active dual sections to the lower and upper bounds would improve accessibility.
Questions for authors
For a representative nonlinear directional loss, how does certified-transform runtime vary with quantile resolution and the required objective precision?
6 comments
Response 2/4 to Reviewer uCyD
Training-size benchmark at fixed . With the asymmetric squared loss , we fit on nested sets of 512, 1,024, and 2,048 distinct curves per arm. The known frozen support used for scoring and the 65,536 independent evaluation draws per arm were fixed across training sizes. Relative LCB shortfall is , with each direction's continuous endpoint as the denominator. Values closer to 0 indicate smaller error.
| Distinct training curves per arm | Relative LCB shortfall | Relative LCB shortfall | Preprocessing and fitting (s) | Evaluation and calibration (ms) | Verification (ms) | Total incl. verification (s), mean [min–max] | Peak CPU process working set (MiB) |
|---|---|---|---|---|---|---|---|
| 512 | 0.1725 | 0.1583 | 3.345 | 1.71 | 65.7 | 3.412 [3.208–3.807] | 239.07 |
| 1,024 | 0.1435 | 0.1414 | 5.211 | 1.62 | 79.3 | 5.291 [4.245–7.301] | 239.38 |
| 2,048 | 0.1241 | 0.1245 | 5.530 | 1.34 | 53.3 | 5.585 [5.302–5.951] | 301.52 |
Stage times average three independently launched single-thread processes per training size and cover both policy directions. Verification checks the support-pair inequalities and compares both LCBs with their continuous truth brackets. Peak memory is the largest whole-process CPU working set across the three runs. The resolution benchmark below retimed all three settings in a separate batch with training fixed at 2,048 curves per arm.
Anonymized stage-by-stage runtime and peak CPU memory figure shows the timing breakdown for this training-size benchmark.
Resolution benchmark on known frozen support (Table R1). Each run uses the same frozen population, asymmetric squared loss , training and independent evaluation indices, and Bernstein calibration. We fit on all 2,048 distinct curves per arm and use the same 65,536 independent evaluation draws per arm. The target score takes the minimum over the known frozen source support. The experiment covers exactly two ordered policy pairs, and . Their positive continuous population lower endpoints are approximately 0.00529622 and 0.02088609, respectively. Relative LCB shortfall is , using each direction's continuous endpoint as the denominator. Values closer to 0 indicate smaller error.
| Binned OT | Binned OT | Relative LCB shortfall | Relative LCB shortfall | Total through verification (s), mean [min–max] | Peak CPU working set (MiB) | |
|---|---|---|---|---|---|---|
| 8 | 0.00506673 | 0.02002606 | 0.12408 | 0.12447 | 5.100 [4.894–5.365] | 348.21 |
| 16 | 0.00522972 | 0.02064784 | 0.09480 | 0.09656 | 7.345 [6.940–7.695] | 348.66 |
| 32 | 0.00527757 | 0.02082110 | 0.08624 | 0.08874 | 11.006 [10.180–11.421] | 464.01 |
All three resolutions were timed anew in the same Conda environment using three independently launched single-thread processes per . Each time includes both directions and numerical verification. The memory column gives the largest CPU process working set across the three runs.
The binned OT values increase toward the continuous endpoints at the tested resolutions. From to , the binned OT shortfall fell from 4.33% to 0.35% in the direction and from 4.12% to 0.31% in the direction. Increasing from 16 to 32 reduced relative LCB shortfall by 0.86 and 0.78 percentage points, respectively, and added about 3.66 s to mean total time. Mean preprocessing and fitting rose from 7.225 to 10.888 s and accounted for nearly all of the increase. These measurements apply to the frozen support, the two directions, and the three resolutions tested.
For Question 1, Appendix K.3.6 (Table 25) reports a separate full-cone certification experiment for the same loss. With a budget of 129 nodes per query, all 16 queries at met objective bracket widths of and in 2.916 s and 3.085 s, respectively. At , the transform stage took 5.073 s and 8.229 s, with 14/16 and 3/16 queries meeting the respective targets. At , it took 13.312 s and 8.554 s, with 3/16 and 2/16 meeting them. For settings with unmet targets, elapsed times include budget-limited queries and cannot establish time to the requested precision. Table R1 instead measures the cost of varying for a finite support scan, which has no full-cone objective tolerance .
Response 3/4 to Reviewer uCyD
Accuracy target and computational cost. Equation (16) bounds the expected worst-pair positive shortfall of the completed-anchor lower certificate. Under its assumptions, the bound separates four contributions:
\mathbb E\sup_{(\pi,\pi')\in\Pi^2} \bigl\\{\Theta^L_{c_h}(\pi,\pi')-L_\alpha^{\mathrm{comp}}(\pi,\pi')\bigr\\}_+ \\ \lesssim\\ & \underbrace{(\ell\kappa\underline e+1)^{-1/s}}_{\text{outer-law learning}} +\underbrace{K^{-1}+\eta+\varepsilon_{\mathrm{opt}}}_{\text{numerical error}}\\\\ &+\underbrace{q_{\mathrm{ev}}}_{\text{nuisance remainder}} +\underbrace{\frac{1}{\underline e} \sqrt{\frac{\log(N_\Pi\vee 2)+\log(2/\alpha)}{m}}}_{\text{evaluation and calibration}}. \end{aligned}$$ Here $\ell$ and $m$ are the training and evaluation sample sizes, $\kappa$ is the minimum cell mass, $\underline e$ is the overlap lower bound, $s$ is the quantization exponent, and $N_\Pi$ counts the distinct policy action vectors. For known-propensity IPW, $q_{\mathrm{ev}}=0$. The three numerical terms come from quantile discretization ($K^{-1}$), the source-anchor covering radius ($\eta$), and the certified residual of the finite training OT solve ($\varepsilon_{\mathrm{opt}}$). Training anchors already give a globally feasible lower dual. Completion improves its tightness. **The explicit completion grid grows exponentially in $1/t$.** Here $t$ is the numerical error budget. Taking $t$ at the scale of the statistical error in Eq. (16) preserves the statistical rate. For fixed outcome range $D>0$ and loss Lipschitz constant $L_h>0$, the choices $K=\lceil16L_hD/t\rceil$, $\eta=t/(8L_h)$, and $\varepsilon_{\mathrm{opt}}\le t/2$ ensure $4L_hD/K+2L_h\eta+\varepsilon_{\mathrm{opt}}\le t$. Both $K$ and the number of grid intervals per coordinate, $\lceil D/\eta\rceil$, then grow as $1/t$. The number of nondecreasing grid vectors is $$J_{K,\eta}=\binom{K+\lceil D/\eta\rceil}{K} =\exp\\{\Theta(1/t)\\}\qquad (t\downarrow0).$$ Appendix E.5 constructs and scores every one of these anchors. Scanning $J_{\mathrm{fit}}$ fitted target sections per anchor costs $O(J_{K,\eta}J_{\mathrm{fit}}K)$ in total. The anchors carry zero transport mass, so the exponential growth is in the completion step. **Cost of the transform by loss and support.** For a query $r$, the full-cone transform minimizes $c_K(x,r)-A(x)$ over the monotone quantile cone, where $A(x)=\min_j\\{c_K(x,y_j)-\beta_j\\}$ is the fitted source potential. - **General convex loss on the full cone.** For this separate transform, Appendix E.6 uses branch-and-bound on a potentially nonconvex objective. The lower endpoint of a bracket of width $\tau$ gives a feasible score with objective error at most $\tau$. The number of boxes explored depends on $K$, $\tau$, and the instance. - **Directional linear loss.** The directed triangle inequality makes the transform equal to $-A(r)$, computed in $O(J_{\mathrm{fit}}K)$ per query. - **Symmetric squared loss.** The common quadratic term cancels, giving an LP with $K+1$ variables and $J_{\mathrm{fit}}+O(K)$ constraints per query. - **Known finite support, as in the benchmark.** For encoded support sizes $s_0,s_1$, building a directional cost matrix takes $O(Ks_0s_1)$ time and $O(s_0s_1)$ memory. After the separate empirical OT fit, compute $g(y)=\min_{x\in S_0}\\{c_K(x,y)-f(x)\\}$ for all target atoms in $O(s_0s_1)$ time with the cached matrix. The minimum enforces feasibility for all support pairs. The implementation applies a $2\times10^{-10}$ downward guard to each score. The full-support oracle fits every frozen curve at its population weight, so its training and population laws coincide. In both directions its population dual mean is within about $2.0\times10^{-10}$ of the binned OT value. Dual feasibility and conservative binning (Theorem E.1) bound the population score by the continuous endpoint. Binning can leave a gap to that endpoint, and the final LCB subtracts an empirical Bernstein radius from the independently evaluated score. Conditional on fitting, empirical Bernstein calibration on the independent draws gives at least 99% simultaneous coverage for the two directions at each training size by allocating a failure probability of 0.0025 to each of the four arm means. We propose stating the loss and support conditions for these computational routes after Eq. (16) and adding Table R1 to the experimental discussion, with a reference to the separate full-cone results in Appendix K.3.6.
Response 1/4 to Reviewer uCyD
wk1
We revised the prose and transitions in Section 1. The activity example shows how equal means and Wasserstein barycenters can conceal differences across individuals. The revised text connects this example to the range of costs across compatible cross-person matchings and explains what governs coverage and endpoint accuracy. The contribution list now leads with the minimax result for endpoint accuracy.
We redrew Figures 1 and 2 and rewrote their captions.
Figure 1 (Section 1). From individual distributions to a matching interval. Three panels connect the activity example to the matching interval and show how global feasibility supports coverage and how outer-law geometry governs endpoint accuracy.
Figure 2 (Section 3). The inference workflow. The figure shows training, global certification, independent evaluation, and simultaneous calibration in sequence.
We also revised the caption of Figure 3, submitted PDF, p. 9 to explain the two panels on calibration overhead and normalized endpoint bounds.
wk2
Joint response to WK2 and Question 1. The explicit full-cone grid used to attain the accuracy in Eq. (16) grows exponentially in the inverse numerical tolerance. We benchmark an asymmetric squared loss, a nonlinear convex loss whose full-cone transform can be nonconvex. On known finite support, a direct support scan bypasses grid completion and yields informative lower certificates in both directions in 5.100–11.006 seconds on average across the three tested resolutions, including verification. For two special classes, the full-cone transform itself is tractable: a direct scan for directional linear losses and a linear program for the symmetric squared loss.