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 “"Normalizing Flows"”.
-
Needles in the Quantum Haystack: CMS Anomaly Detection with Normalizing Flows
… density estimation algorithm, neural spline normalizing flows, into an anomaly detection strategy called Quasi-Anomalous Knowledge (QUAK), which allows us to take advantage of signal priors in addition to QCD background priors. The introduction of a signal prior allows us to learn the …
-
Probing the Nonperturbative Physics of QCD with Normalizing Flows and a moderate number of Pions
… of methods from machine learning (namely normalizing flows) in order to accelerate sampling. This approach has the promise of eliminating issues such as critical slowing down, as well as introducing novel tools and methods that enable methods of calculation that would be possible otherwise.
-
Non-Gaussian Factor Graph Inference for Robotic Navigation
… With this conditional sampling framework, we use normalizing flows to learn local conditional distributions on cliques of the Bayes tree. The normalizing flows exploit the expressive power of neural networks, and train a coupling function that connects a low-dimensional non-Gaussian distribution …
-
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 …
-
Generalized flow-based variational autoencoder networks for anomaly detection in multivariate time series
… approximations are explored through the use of normalizing flows. By applying normalizing flow transforms to the latent variables of a variational autoencoder, the true latent distribution can be more richly modeled and learned, thus enabling better metrics for anomaly detection. This thesis …
-
Analyzing Multimodal Interactions through Improved Partial Information Decomposition Estimation
… Partial Information Decomposition (PID) using normalizing flows, with the ability to scale well to high-dimensional data. We also develop a new framework for estimating pointwise PID, which provides insights into how individual data points contribute to information sharing and interactions …
-
Machine Learning for Physics: from Symbolic Regression to Quantum Simulation
… for faster bosonic quantum simulation using normalizing flows to simulate a compressed representation of a quantum state, and 2) OccamNet, a framework for scientific discovery through novel algorithms for efficient and parallelizable symbolic regression. Our methods demonstrate the potential …
-
Smooth Interpolation on Series of Measures
… We present a model based on continuous normalizing flows which simultaneously interpolates within and across time steps. Our model’s trajectories have a number of desirable geometric properties such as smoothness and continuity. We also provide an extension of our model, linking it to …
-
Max-Stable Processes, Measure Transport & Conditional Sampling
… sampling and simulation methods, such as normalizing flows and measure transport, are crucial for estimating extremes at un-monitored sites or under specific conditions, thereby improving our understanding and risk management strategies. The goal of this thesis is to make significant …
-
Modeling Astrophysical and Large-Scale Structure Signatures in Axion Cosmologies
… we deploy generative machine learning models (normalizing flows) to characterize neutral hydrogen distributions in post-reionization FDM model Universes. Our findings indicate that extreme FDM models can be ruled out based solely on their low neutral hydrogen (HI) abundance. We quantify the HI …
-
Stochastic prediction in sequential high-dimensional observation space
… We also provide an alternative method based on normalizing flows. To the best of our knowledge, these models are the first to provide an effective stochastic multi-frame prediction for real-world videos. We demonstrate the capability of these methods in predicting detailed future frames of …
-
Scalable Full Posterior Inference for Uncertainty-Aware Robot Perception
… inference of joint posterior through learning normalizing flows on the Bayes tree, and 3) reference solutions to full posterior inference via nested sampling. Additionally, we develop a streaming platform that connects mobile devices and servers through web applications to conduct live demos of …
-
Decoding Dark Matter Halos through the Lens of Machine Learning
… Next, I develop a generative model using normalizing flows and recurrent neural networks to reconstruct the mass assembly histories of DM halos in cosmological simulations. Furthermore, I utilize variational diffusion models and Transformer-based neural networks to perform point-cloud …
-
Deep learning methods for large-scale physics
… of a mathematical connection between continuous normalizing flows and optimal transport. Another problem of recent interest in geology is modeling the mapping from shortwave infrared (SWIR) data to abundances of critical minerals provided by a scanning electron microscope. The work in this thesis …
-
Variational Inference in Dynamical Systems
… a more flexible class of posteriors, based on normalizing flows, which can be easily evaluated, sampled, and optimised. The other method, Variationally Coupled Dynamics and Trajectories (VCDT), tackles the factorisation assumption, leveraging sparse Gaussian processes and their variational …