Metod Jazbec: Scalable Gaussian Process Variational Autoencoders
V četrtek, 12. 1. 2023, ob 14:15 bo v okviru seminarja VeSFiM potekalo predavanje Metoda Jazbeca (University of Amsterdam) z naslovom Scalable Gaussian Process Variational Autoencoders po videokonferenčnem sistemu ZOOM.
Povzetek: Conventional variational autoencoders fail in modeling correlations between data points due to their use of factorized priors. Amortized Gaussian process inference through GP- VAEs has led to significant improvements in this regard, but is still inhibited by the intrinsic complexity of exact GP inference. We improve the scalability of these methods through principled sparse inference approaches. We propose a new scalable GP- VAE model that outperforms existing approaches in terms of runtime and memory footprint, is easy to implement, and allows for joint end-to-end optimization of all components.
Povezava na videokonferenčni sistem ZOOM: https://uni-lj-si.zoom.us/j/95492285750 ID: 954 9228 5750 Vljudno vabljeni!