---
title: Diffusion Schrödinger Bridge (DSB)
url: https://www.emergentmind.com/topics/diffusion-schrodinger-bridge-dsb
type: topic
---

# Diffusion Schrödinger Bridge (DSB)

A Diffusion Schrödinger Bridge (DSB) is a stochastic-process-based framework that solves the problem of probabilistically matching two distributions in finite time by minimally steering a reference diffusion process—such as Brownian motion—between prescribed start and end marginals. The DSB framework constitutes the dynamic, entropy-regularized generalization of optimal transport (OT) and underpins a range of modern generative modeling and inference methodologies. It generalizes both classical denoising diffusion models and entropic optimal transport, provides a principled link to stochastic control, and supports rich algorithmic variants for continuous, discrete, unbalanced, and manifold-valued domains.

## 1. Mathematical Foundations and Core Formulation

Consider two probability distributions $\pi_0$ and $\pi_1$ on $\mathbb{R}^d$ at times $t=0$ and $t=1$. The DSB problem is to find a path measure $\mathbb{P}$ over trajectories $(X_t)_{t\in[0,1]}$, absolutely continuous with respect to a reference diffusion process $\mathbb{Q}$ (e.g., Brownian motion or an SDE with given drift), that transports $\pi_0$ to $\pi_1$ while minimizing the relative entropy (KL divergence) to $\mathbb{Q}$:
\[
\mathbb{P}^{\rm SB} = \arg\min_{\mathbb{P} \in \mathcal{P}(C)} \ \mathrm{KL}(\mathbb{P} \Vert \mathbb{Q})
\quad \text{s.t.} \quad \mathbb{P}(X_0 \in dx) = \pi_0(dx),\ \mathbb{P}(X_1 \in dx) = \pi_1(dx)
\]
where $C = C([0,1], \mathbb{R}^d)$ [2503.21756][2403.14623][2106.01357].

Equivalently, the DSB can be formulated as a stochastic optimal control problem: minimize the expected control energy needed to steer the reference SDE to the desired endpoint distributions,
\[
dx_t = f(x_t, t)\,dt + u_t(x_t)\,dt + \sigma(t)\,dW_t
\]
with cost
\[
\E_{\mathbb{P}}\left[\frac{1}{2} \int_0^1 \|u_t(x_t)\|^2 dt\right],
\]
s.t. $x_0 \sim \pi_0$, $x_1 \sim \pi_1$. The optimal control $u_t^*$ is realized as a gradient of certain potentials and relates to score functions [2503.21756][2409.11651][2506.08065].

This setting generalizes classical static OT and, in the zero-noise limit, recovers the Benamou–Brenier dynamic OT [2303.16852]. DSB also connects directly to entropy-regularized OT through the static coupling of endpoints via the reference path measure [2503.21756].

## 2. Algorithmic Principles and Neural Parameterization

Practical DSB solvers exploit the structure of IPF (iterative proportional fitting) or IMF (iterative Markovian fitting). The standard numerical procedure alternates between:

- **Reciprocal/bridge projection:** Fix the joint endpoints, reconstruct paths via the reference bridges.
- **Markovian/diffusion projection:** Given the path marginals, fit a Markov SDE minimizing KL divergence subject to the required marginals.

In the discrete setting, this involves alternately updating forward and backward SDEs (or Markov chains) with learned, time-dependent drift terms [2106.01357][2403.14623][2503.21756]. For continuous state spaces, the drift at each iteration is parameterized via neural score models or mean prediction networks, typically U-Nets or MLPs, depending on the data domain [2303.16852][2409.11651]. The main regression objectives are denoising-score-matching for score estimation and mean-matching for transition means.

Bidirectional alternation and IPF-like updates ensure monotonic reduction in endpoint-matching error and overall KL divergence [2503.21756][2106.01357]. In practice, many state-of-the-art approaches (e.g., DSBM, IPMF) utilize minibatch Sinkhorn coupling, Sinkhorn flows, or stochastic approximation to enforce endpoint constraints efficiently [2303.16852][2410.02601].

## 3. Theoretical Guarantees and Generalizations

**Convergence

Source: https://www.emergentmind.com/topics/diffusion-schrodinger-bridge-dsb