37 citations · 64 across the 13 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
stat.ML2019
High Mutual Information in Representation Learning with Symmetric Variational Inference
Micha Livne, Kevin Swersky, David J. Fleet
We introduce the Mutual Information Machine (MIM), a novel formulation of representation learning, using a joint distribution over the observations and latent state in an encoder/d…
cs.LG2019★ 2 cited
MIM: Mutual Information Machine
Micha Livne, Kevin Swersky, David J. Fleet
We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design p…
cs.LG2019
TzK: Flow-Based Conditional Generative Model
Micha Livne, David Fleet
We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-condi…