Generalized ELBO with Constrained Optimization , GECO

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Shaping Belief States with Generative Environment Models for RL (2019, background): “We found empirically that a modified ConvDRAW in combination with GECO [28] works well in practice, which allows us to learn stable belief-states while maintaining good sample quality.”
Unsupervised Model Selection for Variational Disentangled Representation Learning (2019, background): “It is known that even vanilla VAEs (Kingma & Welling, 2014; Rezende et al., 2014) enter the “polarised regime”, which is often cited as one of their shortcomings (e.g. see Rezende & Viola (2018)).”
Hamiltonian Generative Networks (2019, methodology): “Furthermore, we introduce a Lagrange multiplier in front of the KL term and optimise it using the same method as in Rezende & Viola (2018).”
Continuous diffusion for categorical data (2022, background): “…with L2 regularisation, margin penalties (Dieleman et al., 2021; Donahue et al., 2019), as well as automatic adaptation of the L2 penalty weight to target unit variance for the embedding vector components (Dieleman et al., 2021; Rezende and Viola, 2018), but found that normalisation works best.”