Monte Carlo variational auto-encoders
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better variational approximations, it has been proposed to use importance sampling to get a lower variance estimate of the evidence...
Main Authors: | Thin, A, Kotelevskii, N, Durmus, A, Panov, M, Moulines, E, Doucet, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Journal of Machine Learning Research
2021
|
Similar Items
-
Auto-encoding sequential Monte Carlo
by: Le, T, et al.
Published: (2018) -
Hamiltonian Variational Auto-Encoder
by: Caterini, A, et al.
Published: (2019) -
Sequential Monte Carlo samplers
by: Del Moral, P, et al.
Published: (2006) -
Monte Carlo methids for signal processing
by: Doucet, A, et al.
Published: (2005) -
Controlled sequential Monte Carlo
by: Heng, J, et al.
Published: (2020)