12
IRUS Total
Downloads
  Altmetric

Inverse-free inference and reliable uncertainty quantification with gaussian processes

File Description SizeFormat 
Popescu-S-2023-PhD-Thesis.pdfThesis42.32 MBAdobe PDFView/Open
Title: Inverse-free inference and reliable uncertainty quantification with gaussian processes
Authors: Popescu, Sebastian Gabriel
Item Type: Thesis or dissertation
Abstract: Standard machine learning research involves running experiments on training and testing data stemming from the same distribution, which is usually a data generating pipeline that involves clean data occurring in a clearly defined environment. However, in real-life scenarios models face unexpected distributions shifts, with the imperative need to discern unknown ``unknowns'', more specifically to detect outliers. Deep Neural Networks have proven their prowess in correctly classifying objects, albeit the lack of uncertainty, of a framework to incorporate prior knowledge and the reliance on large datasets. Bayesian methods are considered to fix said issues, with Gaussian Processes being an example of models that place function-space priors, finding usage due to their uncertainty quantification properties. Associated drawbacks to Gaussian Processes range from designing data-specific kernels to distributional mismatch between Gaussian predictive distribution and the real data generation distribution. This thesis posits that deep Gaussian Processes represent the optimal choice towards adequate out-of-distribution detection, as they circumvent aforementioned issues due to hierarchical nature. Firstly, we investigate deep Gaussian Processes' capabilities to properly detect outliers and propose changes to enhance out-of-distribution detection. Subsequently, we introduce a probabilistic layer that acts as a drop-in replacement for layers in convolutional architectures, with the property of reliably propagating uncertainty forward. We re-frame medical imaging prediction tasks as outlier detection, showing that our probabilistic module is more capable of detecting pathologies in MR scans as outliers given healthy samples in the training set. To ensure the competitiveness of our models we need to address the computational drawbacks associated to training Gaussian Processes. We propose an inverse-free variational lower bound to sparse Student-t Processes, showing through various experiments similar behaviour to matrix-inversion dependent models. Lastly, we dwell on future research pathways and applications, concluding that safe machine learning deployment is conditioned on probabilistic models with strong uncertainty guarantees.
Content Version: Open Access
Issue Date: Jun-2023
Date Awarded: Nov-2023
URI: http://hdl.handle.net/10044/1/108227
DOI: https://doi.org/10.25560/108227
Copyright Statement: Creative Commons Attribution Licence
Supervisor: Sharp, David
Glocker, Ben
Cole, James
Department: Department of Brain Sciences
Publisher: Imperial College London
Qualification Level: Doctoral
Qualification Name: Doctor of Philosophy (PhD)
Appears in Collections:Department of Brain Sciences PhD Theses



This item is licensed under a Creative Commons License Creative Commons