2026-09-18T17:35:51Zhttps://api.repository.cam.ac.uk/server/oai/request

oai:www.repository.cam.ac.uk:1810/3862252025-07-05T00:43:56Zcom_1810_219481com_1810_256065col_1810_219482

Deep learning for grouped data https://doi.org/10.17863/CAM.119538 Iliescu, Dan Andrei Wischik, Damon This dissertation explores the problems inherent in applying deep learning algorithms to groups of data. My claim is that groups should be represented as random variables whose values should be inferred from data. This approach has the potential to unlock solutions in many important domains of machine learning, including disentangling the generative factors of data, performing missing data imputation, or training robust predictors. However, grouped data also comes with challenges, especially when the data is high-dimensional and non-linear. Addressing these limitations is the focus of the technical contributions of my doctorate. University of Cambridge 2024-07-03 Thesis Doctoral Doctor of Philosophy (PhD) https://www.repository.cam.ac.uk/handle/1810/386225 https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/73a312f3-6c94-4323-96c9-0f1889bd0e97/download 39e62c3b09732567fec388b9dc14e663 https://apollo8-f-pro.lib.cam.ac.uk/bitstreams/95bcb94c-258e-4c1b-9305-5912d85590c0/download 87eda9de84448d1f82354d60eee3eb5f http://purl.org/NET/rdflicense/allrightsreserved deep learning variational autoencoders transformers machine learning bayesian inference causal inference self supervised learning latent space disentanglement missing data imputation unsupervised domain adaptation