3 papers
cs.LG2023
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
Zhongtian Chen, Edmund Lau, Jake Mendel +2
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theory (SLT). We derive a closed formula for the theoretical loss and, in the case of…
eess.IV2023
Technical outlier detection via convolutional variational autoencoder for the ADMANI breast mammogram dataset
Hui Li, Carlos A. Pena Solorzano, Susan Wei +1
The ADMANI datasets (annotated digital mammograms and associated non-image datasets) from the Transforming Breast Cancer Screening with AI programme (BRAIx) run by BreastScreen Vic…
stat.ML2023
Variational Bayesian Neural Networks via Resolution of Singularities
Susan Wei, Edmund Lau
In this work, we advocate for the importance of singular learning theory (SLT) as it pertains to the theory and practice of variational inference in Bayesian neural networks (BNNs)…