List your company
ResearchFormerly WizWand

Density Estimation on Dynamic MNIST (test)

22.84NLLByPE-ConvHVAE
22.777223.201123.62524.0489Jul 20, 2021
Updated 8mo ago

Evaluation results

MethodLinks
ByPE-ConvHVAEArchitecture=CNN with two stochastic layers, IWAE samples=5000, Pseudocoreset size=5002021.0722.84
ConvHVAEArchitecture=CNN with two stochastic layers, Prior=Exemplar prior, IWAE samples=5000, Exemplar size=5002021.0722.92
ConvHVAEArchitecture=CNN with two stochastic layers, Prior=VampPrior, IWAE samples=5000, Pseudo-inputs size=5002021.0722.94
ConvHVAEArchitecture=CNN with two stochastic layers, Prior=Gaussian, IWAE samples=50002021.0723.16
ByPE-HVAEArchitecture=MLP with two stochastic layers, IWAE samples=5000, Pseudocoreset size=5002021.0723.48
HVAEArchitecture=MLP with two stochastic layers, Prior=VampPrior, IWAE samples=5000, Pseudo-inputs size=5002021.0723.54
HVAEArchitecture=MLP with two stochastic layers, Prior=Exemplar prior, IWAE samples=5000, Exemplar size=5002021.0723.58
ByPE-VAEArchitecture=MLP with two hidden layers, IWAE samples=5000, Pseudocoreset size=5002021.0723.61
VAEArchitecture=MLP with two hidden layers, Prior=VampPrior, IWAE samples=5000, Pseudo-inputs size=5002021.0723.65
HVAEArchitecture=MLP with two stochastic layers, Prior=Gaussian, IWAE samples=50002021.0723.82
VAEArchitecture=MLP with two hidden layers, Prior=Exemplar prior, IWAE samples=5000, Exemplar size=5002021.0723.83
VAEArchitecture=MLP with two hidden layers, Prior=Gaussian, IWAE samples=50002021.0724.41