Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models.
Justin BayerMaximilian SoelchAtanas MirchevBaris KayalibayPatrick van der SmagtPublished in: ICLR (2021)
Keyphrases
- latent variable models
- latent variables
- graphical structure
- latent dirichlet allocation
- hidden markov models
- bayesian networks
- hidden variables
- real valued
- structured prediction
- learning problems
- probabilistic model
- probabilistic inference
- bayesian inference
- text data
- principal component analysis
- topic models
- random variables
- discriminative learning
- latent space
- support vector