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 20 of 321 for “"Wasserstein"”.
-
Wasserstein Adversarial Robustness
… perturbations under the $\ell_p$ metric, Wasserstein distance, which takes geometry in pixel space into account, has long been known to be a suitable metric for measuring image quality and has recently risen as a compelling alternative to the $\ell_p$ metric in adversarial attacks. …
-
Optimization in Wasserstein Spaces
… and variational analysis literature to equip the Wasserstein space (i.e., the space of probability measures endowed with the Wasserstein distance) with a variational structure, both by considerably extending existing results and introducing novel tools. Our theoretical analysis culminates in …
-
Unsupervised Multilingual Alignment using Wasserstein Barycenter
… we propose to align languages through their Wasserstein barycenter. Our motivation behind this is that we can encapsulate information from all languages in the barycenter and facilitate bilingual alignment. We evaluate our method on standard benchmarks and demonstrate that our method …
-
Wasserstein Distortion: Unifying Fidelity and Realism
We introduce a distortion measure for images, Wasserstein distortion, that simultaneously generalizes pixel-level fidelity on the one hand and realism or perceptual quality on the other through a width parameter σ. Wasserstein distortion arises from an information theoretical effort of unifying …
-
On curvature conditions using Wasserstein spaces
… interpolation inequality along geodesics in p-Wasserstein spaces is given and a new curvature condition on abstract metric measure spaces is defined. In the second part of the thesis a proof of the identification of the q-heat equation with the gradient flow of the Renyi (3-p)-Renyi entropy …
-
Distributionally robust binary classifier under Wasserstein distance
… with the radius calculated as per the Wasserstein distance. We derive the tractable formulation for the general problem. When focusing on the support vector machine (SVM), the general problem boils down to an easy-to-solve second- order cone programming problem. The robustified SVM is …
-
Vietoris–Rips metric thickenings and Wasserstein spaces
… then K can be interpreted as a subset of the Wasserstein space of probability measures on X. Such spaces are called simplicial metric thickenings, and a prominent example is the Vietoris–Rips metric thickening. In this work we study these spaces from three perspectives: metric geometry, …
-
Distributionally Robust Learning under the Wasserstein Metric
… Robust Optimization (DRO) under the Wasserstein metric. The learning problems that are studied include: (i) Distributionally Robust Linear Regression (DRLR), which estimates a robustified linear regression plane by minimizing the worst-case expected absolute loss over a probabilistic …
-
Deep generative models via explicit Wasserstein minimization
… target distributions, with the goal of a small Wasserstein distance (or other optimal transport costs). The approach is based on two principles: (a) if the source randomness of the network is a continuous distribution (the “semi-discrete” setting), then the Wasserstein distance is realized by a …
-
Generative modeling using the sliced Wasserstein distance
… to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence. Here, we consider an alternative formulation for generative modeling based on random projections which, in its simplest form, results in a single objective rather than a saddlepoint …
-
Optimal Transport, Congested Transport, and Wasserstein Generative Adversarial Networks
… approximates a distribution $\nu$ of real data. Wasserstein GANs with Gradient Penalty (WGAN-GP) [GAA+17] were designed to update $\mu$ by computing and then minimizing the Wasserstein 1 distance between $\mu$ and $\nu$. In the first part of this thesis we show that in fact, WGAN-GP do not …
-
Statistical Inference for Fréchet Regression on Bures-Wasserstein Manifold
Modern scientific applications increasingly generate data that take values in non-Euclidean spaces, including covariance matrices in neuroimaging, probability distributions in single-cell genomics, and correlation structures in network analysis. Classical regression methods, designed for Euclidean …
-
Adapted Wasserstein distances and applications to distributionally robust optimization
This thesis studies adapted Wasserstein distances and their applications to distributionally robust optimization (DRO) problems in a dynamic context. In Chapter 3, we propose a transfer principle to study the adapted 2-Wasserstein distance between stochastic processes. We obtain an explicit formula …
-
A MULTI-LOSS WASSERSTEIN GAN FRAMEWORK FOR GEOSTATISTICAL SIMULATION
… This thesis introduces a Multi-loss Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) framework as an innovative tool for geostatistical simulation. The proposed framework leverages the WGAN-GP architecture alongside multi-loss functions, including feature …
-
Algebraic statistics: Problems in phylogenetics and wasserstein distance optimization
… motion tree models, and the computation of Wasserstein distance to statistical models. The first contribution characterizes the phylogenetic invariants of group-based Cavender-Farris-Neyman (CFN) models on level-1 phylogenetic networks. Building on recent work that reduces the study of …
-
Gilieji generatyviniai modeliai Baltijos akcijų grąžoms: Empirinis Wasserstein GAN vertinimas /
… vanishing gradients, and mode collapse. Wasserstein GAN (WGAN) introduces the Wasserstein distance as the objective function, ensuring smoother gradients and more stable training even when distributions differ significantly. The gradient penalty method enforces the Lipschitz constraint …
-
Wasserstein Autoencoders with Mixture of Gaussian Priors for Stylized Text Generation
… Processing (NLP). Variational autoencoders and Wasserstein autoencoders are two widely used methods for text generation. New research efforts focus on improving the quality of the generated samples for these two methods. While Wasserstein autoencoders are effective for text generation, they are …
-
Reproducing-Kernel Hilbert space regression with notes on the Wasserstein Distance
… L2 error of our estimators with respect to a Wasserstein ball of probability measures centred at the covariate distribution. This leads us to investigate the extreme points of Wasserstein balls. In Chapter 3, we provide bounds on our estimators both when the regression function is unbounded …
-
Market making through reinforcement learning and Wasserstein DRO : an entropy-regularized approach
… learning, including reinforcement learning and Wasserstein distributionally robust optimization (DRO), along with background on classical market making frameworks in financial mathematics. The second part proposes a reinforcement learning framework for options market making, incorporating …
Page 1 of 17