We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions. Two generative models are proposed. One uses EOT cost directly in an one-shot optimization problem and the other uses EOT cost iteratively in an adversarial game...
The present work investigates a new relative entropy-regularized algorithm for solving the optimal transport on a graph problem within the randomized shortest paths formalism. More precisely, a unit flow is injected into a set of input nodes and collected from a set of output nodes with specified...
Entropy regularized TRPOs and their variants add a proper entropy regularization term [16] to their objectives. This is believed to help with exploration because it encourages the agent to select policies more randomly [37], and hence the agent’s performance improves. 2.2.1. On-policy entropy...
We study Benamou's domain decomposition algorithm for optimal transport in the entropy regularized setting. The key observation is that the regularized variant converges to the globally optimal solution under very mild assumptions. We prove linear convergence of the algorithm with respect to the ...
Wasserstein distanceoptimal transportdensity forecastingmodel combinationWe propose probability and density forecast combination methods that are defined using the entropy regularized Wasserstein distance. First, we provide a theoretCumings-Menon, RyanShin, MinchulSocial Science Electronic Publishing...
The "proximity" between probability laws is quantified by the Wasserstein distance, a notion pertaining to optimal transport theory. The combination of the classical entropic regularization technique in this field with recent results from convex duality theory allows to reformulate the distributionally ...
We obtain the explicit form of the entropy-regularized optimal transport cost on multivariate normal and q-normal distributions; this provides a perspective to understand the effect of entropy regularization, which was previously known only experimentally. Furthermore, we obtain the entropy-regularized ...
We propose probability and density forecast combination methods that are defined using the entropy regularized Wasserstein distance. First, we provide a theoretical characterization of the combined density forecast based on the regularized Wasserstein di