- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper capitalizes on recent advances in sliced Optimal Transport plans and proposes a novel regularized optimal transport problem, whose regularization term is the KL divergence between the coupling and the sliced Optimal Transport plan. The computation integrates well into the Sinkhorn solver. Experiments show that it is closer to the exact Optimal Transport plan compared to the entropic Optimal Transport plan.
Critical strengths
- This is a natural extension of entropic optimal transport plan, and it sits well at the intersection of sliced OT and entropic OT.
- The methods are written very clearly and are easy to follow.
- The experiments show consistent improvement in OT plan fidelity over the entropic OT plan at the same regularization level.
Critical weaknesses
-
Theorem 2 is not well justified; see Question 2.
-
Experiments are small-scale, in which exact OT is cheap and fast to compute. This does not match the paper's underlying motivation that exact OT is a computational bottleneck. Experiments at larger sample sizes and in higher dimensions would be more convincing.
Minor:
- Lines 264–265: the adjusted ground cost decreases, rather than increases, the cost of pairs with high probability under the SOT plan.
Questions for authors
- In Figure 2, the SOT plot for the bottom row seems to be wrong. I do not expect the uniform slicing distribution to give such a clean radial matching.
- In its current form, the proof of Theorem 2 does not establish the weak continuity or strict convexity of : depends on through 1D matching and disintegration, which breaks the argument of Feydy et al. (2019) and is not weakly continuous.
- Could the authors state precisely in what sense the SROT divergence recovers "a version of" MMD as ?
[1] Feydy et al. Interpolating between optimal transport and mmd using sinkhorn divergence. AISTATS 2019.