On a $T_1$ Transport inequality for the adapted Wasserstein distance
By: Jonghwa Park
Potential Business Impact:
Helps computers understand how things change over time.
The $L^1$ transport-entropy inequality (or $T_1$ inequality), which bounds the $1$-Wasserstein distance in terms of the relative entropy, is known to characterize Gaussian concentration. To extend the $T_1$ inequality to laws of discrete-time processes while preserving their temporal structure, we investigate the adapted $T_1$ inequality which relates the $1$-adapted Wasserstein distance to the relative entropy. Building on the Bolley--Villani inequality, we establish the adapted $T_1$ inequality under the same moment assumption as the classical $T_1$ inequality.
Similar Papers
A discrete Benamou-Brenier formulation of Optimal Transport on graphs
Information Theory
Finds shortest paths on networks for data.
A transport approach to the cutoff phenomenon
Probability
Makes computer learning faster and more reliable.
A transport approach to the cutoff phenomenon
Probability
Helps computers learn faster without complex math.