Exponential convergence rate for Iterative Markovian Fitting
By: Kirill Sokolov, Alexander Korotin
Potential Business Impact:
Makes computer learning faster and more reliable.
We consider the discrete-time Schr\"odinger bridge problem on a finite state space. Although it has been known that the Iterative Markovian Fitting (IMF) algorithm converges in Kullback-Leibler divergence to the ground truth solution, the speed of that convergence remained unquantified. In this work, we establish for the first time that IMF exhibits exponential convergence with an explicit contraction factor.
Similar Papers
Exponential convergence rate for Iterative Markovian Fitting
Information Theory
Makes computer learning faster and more reliable.
Exponential Convergence Guarantees for Iterative Markovian Fitting
Machine Learning (Stat)
Makes computer models learn faster and better.
Convergence in probability of numerical solutions of a highly non-linear delayed stochastic interest rate model
Probability
Makes financial predictions more accurate with math.