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 59 for “"Normalizing Flows"”.
-
Hamiltonian Normalizing Flows for Particle Systems
… to consumer products. We present an iterative normalizing flow that updates particle coordinates and momenta to sample from target thermodynamic equilibrium distributions. The model is evaluated on its performance in forward sampling (unknown target) and backward inference (known target) in …
-
Modeling sRGB Camera Noise with Normalizing Flows
… propose a new sRGB-domain noise model based on normalizing flows that is capable of learning the complex noise distribution found in sRGB images under various ISO levels. Our normalizing flows-based approach outperforms other models by a large margin in noise modeling and synthesis tasks. We …
-
NORMALIZING FLOWS AIDED VARIATIONAL INFERENCE FOR UNCERTAINTY QUANTIFICATION
Thesis (Ph.D.)--Michigan State University. Statistics - Doctor of Philosophy, 2024
-
Wavelet Flow: Fast Training of High Resolution Normalizing Flows
Normalizing flows are a class of probabilistic generative models which allow for fast density computation, efficient sampling, and are effective at modelling complex distributions like images. A drawback among current methods is their significant training cost, sometimes requiring months of GPU …
-
Investigating the impact of normalizing flows on latent variable machine translation
… could exhibit multi-modal distributive behavior. Normalizing flows are an approach that enables more flexible posterior distribution estimates by introducing a change of variables with invertible functions. They have previously been successfully used in computer vision to enable more flexible …
-
Enhancing Summarization and Causal Discovery: Topic Awareness, Normalizing Flows, and Hierarchical Ensembles
… the significant roles that topic awareness, normalizing flows, and hierarchical ensemble techniques can play in enhancing text summarization and causal discovery, respectively. The first part of the thesis investigates abstractive summarization, introducing PA-TAM, a model that employs a …
-
U(R) PHASE RETRIEVAL, LOCAL NORMALIZING FLOWS, AND HIGHER ORDER FOURIER TRANSFORMS
… In Chapter 2 we develop the concept of local normalizing flows. Normalizing flows provide an elegant approach to generative modeling that allows for efficient sampling and exact density evaluation of unknown data distributions. However, current techniques have significant limitations in their …
-
Expanding the capabilities of normalizing flows in deep generative models and variational inference
… of an expressive family of density models. Normalizing flows, sometimes also referred to as invertible neural networks, are one class of models providing this: they are formulated to be bijective and differentiable, and thus produce a tractable density model via the change-of-variable …
-
Ensemble Kalman filtering and conditional normalizing flows for seismic monitoring via data assimilation
… monitoring. Furthermore, we explore conditional normalizing flow filters (CNFFs) as a nonlinear extension of the EnKF. We examine the typical affine coupling layer used in CNFFs and compare it to the EnKF for a small Gaussian system. Through this theoretical comparison, we propose a different, …
-
Variational Inference for Text Generation: Improving the Posterior
… space and enforcing desired properties and 2) normalizing flows to develop more flexible posteriors to be used during variational inference. We propose a proximity based loss function that helps in disentanglement by regularizing the latent space based on similarity according to a criterion. We …
-
Advancing Probabilistic Models for Approximate and Exact Inference
… likelihood-based probabilistic deep learning is normalizing flows. Normalizing flows use invertible transformations to translate between simple and complex distributions, which allows for exact likelihood calculation and efficient sampling. In order to remain invertible and provide exact …
-
NON-EQUILIBRIUM PROPERTIES OF QUANTUM CHROMODYNAMICS ON THE LATTICE
… problems, which will be referred to as complex normalizing flows. This method belongs to a family of manifold deformation methods, a long-standing approach to alleviate sign problems. The applicability of complex normalizing flows to lattice calculations of our interest, non-equilibrium QCD, …
-
Modeling Structured Data with Invertible Generative Models
… and have been applied to many problems. Normalizing flows are a novel class of deep generative models that allow efficient exact likelihood calculation, exact latent variable inference and sampling. They are constructed using functions whose inverse and Jacobian determinant can be …
-
Efficient Generation of Molecular Boltzmann Distributions with Machine Learning Methods
… how machine learning models, particularly normalizing flows, can accelerate this sampling. Normalizing flows are invertible deep‐generative models that produce novel configurations while providing exact likelihoods. We introduce several normalizing flow architectures that embed the …
-
Simulation-based Inference : From Approximate Bayesian Computation and Particle Methods to Neural Density Estimation
… and machine-learning methods (deep learning and normalizing flows) to develop novel algorithms for inference in implicit Bayesian models. Implicit models are those for which calculating the likelihood function is very challenging (and often impossible), but model simulation is feasible. The …
-
Inductive Bias In Deep Probabilistic Modelling
… connections between Bayesian networks and normalizing flows. We exploit this connection to study some representational aspects of normalizing flows. Finally, we present a new neural network architecture that enforces a monotonic response. We demonstrate the effectiveness of this …
-
Unsupervised outlier detection: new approaches for robust ensembles and interpretability
… both the density estimation capabilities of normalizing flows and the interpretability of decision trees. The method uses normalizing flows to generate pseudo-labels, which then train a decision tree classifier. This provides clear, rule-based classification boundaries for outlier detection, …
-
Uncertainty estimation for adaptable and reliable robotic vision
… A gradient-based method is proposed based on normalizing flows, which provides uncertainty estimates at the pixel-level.The notion of adaptability based on uncertainty is further applied to visuomotor policy learning. A normalizing flow is used to directly produce fine-grained control …
-
Distribution System State Estimation using Data-Driven Approaches
… and fusion issues. A DSSE solver based on normalizing flows is presented. This generative network produces detailed probability density functions (PDFs) for state variables, and is robust to various noises, accurate and computationally efficient. This solver is validated using real world …
Page 1 of 3