Schrödinger Bridge Samplers
This provides a novel Monte Carlo method for sampling and normalization in machine learning, though it appears incremental as it builds on existing Schrödinger bridge and Sinkhorn algorithm concepts.
The authors tackled the problem of approximating a target distribution and estimating its normalizing constant by developing Schrödinger bridge samplers, which iteratively modify a reference Markov process to match the target distribution, reporting preliminary experiments.
Consider a reference Markov process with initial distribution $π_{0}$ and transition kernels $\{M_{t}\}_{t\in[1:T]}$, for some $T\in\mathbb{N}$. Assume that you are given distribution $π_{T}$, which is not equal to the marginal distribution of the reference process at time $T$. In this scenario, Schrödinger addressed the problem of identifying the Markov process with initial distribution $π_{0}$ and terminal distribution equal to $π_{T}$ which is the closest to the reference process in terms of Kullback--Leibler divergence. This special case of the so-called Schrödinger bridge problem can be solved using iterative proportional fitting, also known as the Sinkhorn algorithm. We leverage these ideas to develop novel Monte Carlo schemes, termed Schrödinger bridge samplers, to approximate a target distribution $π$ on $\mathbb{R}^{d}$ and to estimate its normalizing constant. This is achieved by iteratively modifying the transition kernels of the reference Markov chain to obtain a process whose marginal distribution at time $T$ becomes closer to $π_T = π$, via regression-based approximations of the corresponding iterative proportional fitting recursion. We report preliminary experiments and make connections with other problems arising in the optimal transport, optimal control and physics literatures.