In this work, we present a novel volume preserving image segmentation algorithm, which is based on the entropy and Total Variation (TV) regularized optimal transport theory. The volume and classification constraints can be regarded as two measures preserving constraints in the optimal transport. By ...
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...
Macroscopic traffic flow modeling with physics regularized Gaussian process: A new insight into machine learning applications in transportation Transp. Res. B, 146 (2021), pp. 88-110 View PDFView articleView in ScopusGoogle Scholar Yuan et al., 2011 Yuan, Jing, Zheng, Yu, Xie, Xing, Sun,...
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 ...
In this abstract, we report some results of full waveform inversion from an alternative misfit function based on entropy regularized optimal transport. The regularization gives a smooth approximation to the original optimal transport and the regularized optimum can be found efficiently though. Numerical ...
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...
We establish lower and upper bounds on the difference with the unregularized cost of the form $C\\varepsilon \\log (1/\\varepsilon) O(\\varepsilon)$ for some explicit dimensional constants C depending on the marginals and on the ground cost, but not on the optimal ...
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...
Paper tables with annotated results for Synthesis and Analysis of Data as Probability Measures with Entropy-Regularized Optimal Transport
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 ...