.png){kind=icon}
.png){kind=icon}
Return
Plug-in Estimation of Schrodinger Bridges
.png){kind=icon}
PRE
AI
A
J
DOI：10.1137/24M1687340.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a procedure for estimating the Schro\dinger bridge between two probability distributions. Unlike existing approaches, our method does not require iteratively simulating forward and backward diffusions or training neural networks to fit unknown drifts. Instead, we show that the potentials obtained from solving the static entropic optimal transport problem between the source and target samples can be modified to yield a natural plug-in estimator of the time-dependent drift that defines the bridge between two measures. Under minimal assumptions, we show that our proposal, which we call the Sinkhorn bridge, provably estimates the Schro\dinger bridge with a rate of convergence that depends on the intrinsic dimensionality of the target measure. Our approach combines results from the areas of sampling, and theoretical and statistical entropic optimal transport.
Keywords:
entropic optimal transport
Sinkhorn algorithm
Schro
dinger bridges
statistical estimation
Journal
S
IF:
2.6
Papers:
17
Citations:
0
Organization
Cited Papers