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 15 of 15 for “"Wasserstein gradient"”.
-
Weak Solutions to a Fractional Fokker-Planck Equation via Splitting and Wasserstein Gradient Flow
… of a potential field), there is no natural gradient flow formulation for its fractional counterpart, we prove existence of weak solutions to this fractional Fokker-Planck equation by combining a splitting technique together with a Wasserstein gradient flow formulation. An explicit iterative …
-
Parameterized Computational Framework for Density Evolution Equations with Applications in Wasserstein Gradient Flows, Games, and Kushner-Stratonovich Equation
… equations, with application in computing Wasserstein gradient flow (WGF), game dynamics and Kushner-Stratonovich equation. The equations are stemmed from multiple areas including optimal transport (OT) theory, economics and nonlinear filtering. The main part of the thesis contains three …
-
Parameterized Computational Framework for Density Evolution Equations with Applications in Wasserstein Gradient Flows, Games, and Kushner-Stratonovich Equation
… equations, with application in computing Wasserstein gradient flow (WGF), game dynamics and Kushner-Stratonovich equation. The equations are stemmed from multiple areas including optimal transport (OT) theory, economics and nonlinear filtering. The main part of the thesis contains three …
-
Discrepancy Minimization: From Sample Space to Parameter Space
… such as Langevin dynamics which is known as a gradient flow that minimizes<br/>the Kullback-Leibler divergence in Wasserstein geometry. In parameter space, a distribution can be<br/>approximated by fitting a parametric distribution, such as through variational inference. Although both<br/>the …
-
Probabilistic design in the operation of service systems
… sub-distribution structures and propose a gradient-based algorithm using the Wasserstein gradient flow. Our algorithm finds a feasible decomposition that satisfies our optimality condition, with numerical results demonstrating its practicality and insights. Chapter 3 studies an online …
-
Towards Uncertainty and Efficiency in Reinforcement Learning
… probability measure space and formulate it as Wasserstein gradient flows. The proposed method can quantify the uncertainty of value, policy, and constraint functions to provide efficient exploration. </p><p>Running a policy in real environments can be expensive and risky. Besides, there are …
-
An Optimal Transport Approach to Nonlinear Evolution Equations
Gradient flows of energy functionals on the space of probability measures with Wasserstein metric has proved to be a strong tool in studying certain mass conserving evolution equations. Such gradient flows provide an alternate formulation for the solutions of the corresponding evolution equations. …
-
Aggregation-diffusion equations in biology with a gradient flow structure
… the main tools that we need are Otto calculus, Wasserstein gradient flows, viscosity solutions, <em>C</em><sub>0</sub>-semigroup theory, and finite volumes.</p> <p>The models we are interested in show a dichotomy between diffusion and aggregation. Therefore, one of the main question is to …
-
Asymptotic analysis of deep learning algorithms
… scaling regime arises as a consequence of using gradient descent. In particular, we prove linear convergence of gradient descent to a global minimum for the training of deep residual networks. We also show that if the trained weights, as a function of the layer index, admit a scaling limit as the …
-
Generalised variational inference in infinite dimensions
… variational parameters or infinite-dimensional gradient descent methods.</p> <p>Although GVI and in particular VI have previously been employed for function space inference, the infinitedimensional nature of the parameter space has so far been ignored. This has hindered the development of new …
-
Topics in Topological Machine Learning: Persistent Local Homology, Multiset Transformer, and Beyond
… to the movement of persistence diagrams along Wasserstein gradient flows. This study not only bridges TDA and ML but also proposes innovative methodologies and architectures to tackle existing challenges, offering both theoretical and practical contributions to the interdisciplinary field.
-
Learning and inference for distributions: from optimal transport to Markov chain Monte Carlo
… One of its most significant concepts, the Wasserstein distance, has had a substantial impact on machine learning, particularly in the study of Generative Adversarial Networks. Despite its important applications, such as calculating distribution discrepancies, interpolating, and aligning …
-
Theory and computation of Wasserstein geometric flows with application to time-dependent Schrodinger equation
… study of a novel computational framework to the Wasserstein geometric flows, which describe time evolution of probability density functions on the infinite-dimensional Wasserstein manifold. In particular, Wasserstein gradient flows (WGFs) and Wasserstein Hamiltonian flows (WHFs), are the main …
-
Probabilistic uncertainty quantification for structural dynamics under limited data
… the prior is uncertain, based on interacting Wasserstein Gradient Flows, able to compute the worst-case and optimal priors in the vicinity of a selected prior, and their associated posteriors.</p>
-
On a classical solution to the master equation of a first order mean field game
… require further results of the calculus on the Wasserstein space that has been advanced recently by Gangbo et. al. [GC17; Gan18].