![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
Failure Modes of Variational Autoencoders and Their Effects on Downstream TasksAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Elre Oldewage. Variational Auto-encoders (VAEs) are deep generative latent variable models that are widely used for a number of downstream tasks—semi-supervised learning, learning compressed and disentangled representations, adversarial robustness. VAEs are widely used because they are easy to implement and train; in particular, the common choice of mean-field Gaussian (MFG) approximate posteriors for VAEs (MFG-VAE) results in an inference procedure that is straight-forward to implement and stable in training. Unfortunately, a growing body of work has demonstrated that MFG -VAEs suffer from a variety of pathologies, including learning un-informative latent codes and un-realistic data distributions. When the data consists of images or text, we often rely on “gut checks” to ensure the quality of the learned latent representations and generated data is high, but for numeric data (e.g. medical EHR data), we cannot rely on such gut checks. Existing work lacks a characterization of exactly when these pathologies occur and how they impact down-stream task performance. In this talk, we will characterize when VAE training exhibits pathologies (as global optima of the ELBO ) and connect these failure modes to undesirable effects on specific downstream tasks. This talk is part of the Machine Learning Reading Group @ CUED series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsCambridge University United Nations Association Surface, Microstructure and Fracture Talks Film screening - 3 Deewarein (Three Walls)Other talksPredicting outcome for psychotic disorders, using brain connectivity and transcribed speech data TBC Inference from trees: Cybersecurity Settlement Dynamics and Processes of Change in Early Medieval Ireland: New Insights from Radiocarbon Chronologies Deep hedging: Learning Risk-Neutral Implied Volatility Dynamics Charges and Dipoles in Periodic Systems: Here Be Dragons |