Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 4 of 4 for “"Sinkhorn algorithm"”.
-
Geometric methods in computational optimal transport and high-dimensional inference
… connections between geometric structure and algorithmic efficiency. First, a refined analysis of the Sinkhorn algorithm’s convergence properties via the Hilbert projective metric is provided. For probability measures supported on at most n points, it is established that an ε-accurate …
-
A Graph Convolutional Neural Network Based Approach for Object Tracking Using Augmented Detections With Optical Flow
… of the proposed framework is the use of the Sinkhorn algorithm for end-to-end learning of the associations among objects during model training. The network is trained to predict object associations by taking into account constraints specific to the MOT task. Additionally, in order to increase …
-
Advances in Gromov–Wasserstein optimal transport: linearization, multi-marginal generalization, barycenters and transfer operators
… In this cumulative thesis, we develop theory, algorithms and applications of generalized optimal transport models with a primary focus on the Gromov–Wasserstein (GW) transport problem. Figuratively, this transport problem offers a relaxed way of finding a correspondence that retains the …
-
Optimal transport: theory, algorithms and applications
… constantly appearing new variants, insights, algorithms and applications. This is a cumulative thesis, which contains the publications [96, 153, 24, 152, 151] and the unpublished work [154] in the Appendix A. We start with an overview of our corresponding findings and results. First, in …