- Rating
- 1
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
The paper proposes a Bayesian formulation of the Schrödinger Bridge (BSB). BSB introduces a composite projection (Bayesian and posterior projections), which replaces the Markovian projection in Iterative Markovian Fitting. The method uses a Gaussian mixture model for the transport kernel, for which it provides a closed-form update. BSB contributes a method that directly optimizes the KL divergence to the reference bridge without requiring a variational lower bound, and it empirically provides high-quality few-step Schrödinger Bridge solutions. BSB is validated with component ablations and comparisons against baselines on FID, precision and LPIPS, on both image and synthetic datasets. The underlying algorithm is proven to converge.
Critical strengths
The experimental results are promising; SBS compares favorable against baseline and the ablation study show its components all contribute positively.
Critical weaknesses
The paper is hard to follow, mainly because it is not clear which variable the distribution is defined over. Amortizing by predicting its parameters with a network is the key to Theorem 1, so the explanation of on L152 is not sufficient. The claim that SBS analytically performs closed-form Bayesian inference at each time step is too strong. The closed form is only available because of the amortization network and the Gaussian assumption on the data distribution. The theorem then reduces to a case of conjugacy, because the hard parts of inference are hidden in the network and the data assumption. Beyond this main objection, a further weakness of the paper is its notation (see the questions).
Questions for authors
- In what sense does SBS converge faster? And what is SBS claimed to converge faster than? What evidence do you provide in the paper of faster convergence?
- L168: “SB problem suffers from challenges in likelihood optimization and numerical stability”. Which challenges exactly are you referring to here, and how does SBS address them?
- What exactly is the random variable ? is called a posterior, but it is not clear what it is a posterior over.
- In Eqs. 3, 5 and 7, the symbol seems to have two different meanings. Take Eq. 7: the first is a definition (the projection is a kernel), and the second is a constraint (time homogeneity). Is this the right reading?
- In Eq. 17, is the second equality supposed to be there? If so, please provide the derivation.
Minor
in Eq. 3 is not defined. The RHS of Eq. 8 does not depend on .