activity
20182020
most citedMIM: Mutual Information Machine

2 citations · 2 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL2020

SentenceMIM: A Latent Variable Language Model

Micha Livne, Kevin Swersky, David J. Fleet

SentenceMIM is a probabilistic auto-encoder for language data, trained with Mutual Information Machine (MIM) learning to provide a fixed length representation of variable length la…

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.LG20192 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…

cs.CV2018

Walking on Thin Air: Environment-Free Physics-based Markerless Motion Capture

Micha Livne, Leonid Sigal, Marcus A. Brubaker +1

We propose a generative approach to physics-based motion capture. Unlike prior attempts to incorporate physics into tracking that assume the subject and scene geometry are calibrat…

cs.LG2018

TzK Flow - Conditional Generative Model

Micha Livne, David J. Fleet

We introduce TzK (pronounced "task"), a conditional probability flow-based model that exploits attributes (e.g., style, class membership, or other side information) in order to lea…