- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The manuscript correctly identifies a structural degeneracy in the semi-dual formulation and derives a corresponding stability estimate under strong regularity assumptions. However, the novelty is limited, the assumptions exclude most realistic data regimes, the experiments remain confined to synthetic settings where the theory is most favorable, and the critique of prior work is overstated. The overall contribution is incremental and does not meet the bar for acceptance at ICLR.
Critical strengths
-
The paper cleanly isolates the flatness of the semi-dual objective at an optimal map and supplies an explicit stability estimate that does not require the dual potential itself to be optimal. This is a useful clarification for the neural-OT literature.
-
The experimental illustrations (especially the timescale sweeps) make the practical consequence of the degeneracy concrete: one can obtain a good transport map while the potential remains far from optimal. This matches common empirical practice and is presented transparently.
Critical weaknesses
-
Limited novelty and overstated contributions.The core observation—that the semi-dual objective becomes independent of once (i.e., the dual term vanishes when the marginal constraint is satisfied)—is a direct and essentially immediate consequence of the definition of the Lagrangian / semi-dual functional. The same flatness is already visible in classical duality arguments and in the analysis of (2,2)-WGANs / NOT. Framing this as a previously unrecognized “degenerate saddle-point structure” and claiming that existing convergence analyses are invalidated because they assume optimality of overstates the technical advance. The quantitative estimate (Theorem 4) is a reasonable combination of standard strong-convexity / Brenier regularity arguments with a Kantorovich–Rubinstein residual, but it does not rise to a major new theoretical insight.
-
Extremely restrictive assumptions that undermine practical relevance.Theorem 4 requires densities in that are bounded away from zero, domains that are and uniformly convex, and a uniformly Lipschitz family of potentials. These conditions are far stronger than those typically satisfied by the distributions arising in generative modeling (images, tabular data, etc.). The paper itself notes that many real datasets live near lower-dimensional manifolds where Monge maps need not exist (Table 1), yet the main stability result simply assumes the classical Brenier setting. Consequently the claimed explanation of “why more map updates are needed” does not rigorously apply to the regimes in which neural OT is actually used.
-
Experiments are too synthetic and insufficient to support the practical claims.The main figures (1–2) use only 1-D / 2-D Gaussians. The high-dimensional experiments (Appendix E) rely on an ICNN-generated continuous benchmark whose ground-truth map is itself produced by a strongly convex network—the most favorable setting possible for the theory. There are no experiments on real image data, no comparison against competitive baselines (e.g., recent neural OT or flow-matching methods), and no demonstration that the recommended timescale ratio yields measurable gains on downstream generative tasks. The observed phenomenon “map converges while potential diverges” is expected once the constraint is nearly satisfied; showing it on toy Gaussians does not constitute strong empirical support.
-
Technical gaps and imprecise claims about prior work.Several statements about earlier papers (Fan et al., Rout et al., Tarasov et al., Korotin et al., Choi et al.) are presented as exposing fundamental flaws, yet the critique often reduces to “they assumed optimality of the potential.” Because the objective is flat once the map is optimal, those analyses remain valid in the regime they study. In addition, the continuous-time two-timescale system (22) is written down without a rigorous justification that the discrete alternating scheme converges to it, and the constant in the stability estimate is left completely opaque. The claim that the numerical procedure is “equivalent to a constrained optimization problem” is only heuristic; the Lagrangian is non-convex and the interchange of and is not justified under the paper’s own hypotheses.
-
Insufficient significance for a top-tier venue. The paper essentially rediscovers a structural property of the semi-dual formulation, derives a stability bound under classical (and strong) regularity assumptions, and illustrates on synthetic data that the map can converge without the potential. While the observation is correct and the writing is generally clear, the incremental value relative to the already substantial literature on neural OT, two-timescale GAN dynamics, and stability of Brenier maps is modest. The work does not open a new algorithmic avenue, does not relax existing assumptions in a useful way, and does not deliver compelling empirical evidence that the community should change practice.
Questions for authors
please refer to the weaknesses above.
Response to Reviewer 8DSa
1. Novelty and prior work. The flatness itself is elementary and follows from the definition; we do not claim otherwise. Our contribution is making its consequences explicit by rewriting F(ψ,t)=∫c(x,t(x))dμ+∫ψ(y)d(ν−t♯μ) in terms of measures. Two kinds of hypotheses appear in earlier work. Some arguments use optimality of the potential (Rout et al. 2021, Thm 4.3). Since F is independent of ψ at T⋆, nothing in the objective drives ψ toward ψ⋆, and Figs 1-2 show ψ staying away from ψ⋆ while the map converges, so these hypotheses are not enforced by training. Others restrict the potential class (Fan et al. 2021: c-concave; Tarasov et al. 2026: λ-strongly convex). Convexity can be enforced by architecture, but at the cost of expressiveness. Our estimate needs only a uniform Lipschitz bound, so it covers unconstrained networks. Separately, Korotin et al. 2023, Lemma 1 is not about flatness: most likely authors conflated the existence of an infimum with a minimizer in the Monge problem (we provide Table 1 for convenience). Choi at al. 2025 oversee the flatness (Cor. 3.3). That's why we find it useful to formulate as a separate theorem.
On whether (17) follows from earlier works. We would ask the reviewer to indicate how the estimate would follow from results that assume optimality, c-concavity or λ-strong convexity of the potential, because the implication goes in the opposite direction. On a compact domain, c-concave potentials are Lipschitz, with a constant controlled by diam(Y), and potentials of the form ∣y∣2/2−v with v λ-strongly convex and Lipschitz also lie in the uniformly Lipschitz class. So those hypotheses are special cases of ours, while a Lipschitz ψ need not be c-concave, strongly convex or near-optimal. The proof has two parts. Step 2 (App. A) uses λ-strong convexity of the optimal potential v⋆, which comes from the regularity theory (Caffarelli) and is standard. Steps 3-4 are new: they remove ψ from the estimate adding the term dKR(t♯μ,ν). If the reviewer can show that this follows directly from a cited theorem, we will gladly shorten the proof and credit that result.
2. Assumptions. The hypotheses of Thm 4 are the standard setting for regularity of Brenier maps, and they give strong convexity of the dual potential. To our knowledge, estimate (17) is new even in this setting. We agree they exclude manifold-supported data and regard relaxing them as the main open problem. The explanation of why more map steps help (Sec. 4.2) is an interpretation in the regime where the theory applies, not a convergence guarantee for alternating optimization.
3. Experiments. The contribution is theoretical, and the experiments illustrate it rather than prove it. They require a known T⋆ and ψ⋆. We acknowledge that 192-D benchmark benchmark is favorable to the theory by design, and real data has no ground-truth map. The solvers tested (OTP, MongeMap, MaxCorr, OTM) are representative semi-dual NOT formulations (Table 2). Flow matching is related but is a different problem, without the min-max structure we analyze. We do not claim downstream gains from a particular timescale ratio, and we updated abstract in the revision. If the reviewer has specific baselines in mind, we would be glad to add them.
4. Technical points. (a) Interchange of sup and inf. By Thm 3(iii), supψF=+∞ for infeasible t, so inf-sup reduces to the Monge problem. This works for continuous ψ, but not for Lipschitz ψ. We corrected the wording in Sec. 5.5, which now states equivalence for specific Lipschitz constant. (b) The constant. From App. A, Step 4, C=(2/λ)max(1,M), with M=max(2L′,L′⋅diamY). Here λ is the strong-convexity constant of the dual potential depending on the domains and densities, and L′ is a common Lipschitz bound. (c) System (22) is the formal continuous limit of the alternating scheme (first variations of F in t and ψ). We do not prove convergence of the discrete scheme to it, we use it in Discussion as a heuristic.
5. Significance. We see the contribution as the quantitative map-stability estimate that needs no optimal potential, and as a practical diagnostic: map convergence should be verified through dKR(t♯μ,ν) in addition to the objective. Makkuva et al. 2020, Remark 3.4 reports that relaxing convexity constraints performs empirically better. That the map can converge while the potential does not may seem expected once the constraint is nearly satisfied, but it had not been quantified: Thm 4 bounds the map error by the objective gap and marginal mismatch for any ψ in the Lipschitz class, and Remark 2 gives the converse.
6. Ethics flag. We could not find an ethics concern described in the review. Could the reviewer clarify what prompted it?