Timezone: »
We introduce the thermodynamic variational objective (TVO) for learning in both continuous and discrete deep generative models. The TVO arises from a key connection between variational inference and thermodynamic integration that results in a tighter lower bound to the log marginal likelihood than the standard variational evidence lower bound (ELBO) while remaining as broadly applicable. We provide a computationally efficient gradient estimator for the TVO that applies to continuous, discrete, and non-reparameterizable distributions and show that the objective functions used in variational inference, variational autoencoders, wake sleep, and inference compilation are all special cases of the TVO. We use the TVO to learn both discrete and continuous deep generative models and empirically demonstrate state of the art model and inference network learning.
Author Information
Vaden Masrani (University of British Columbia)
Tuan Anh Le (MIT)
Frank Wood (University of British Columbia)
More from the Same Authors
-
2021 : TITRATED: Learned Human Driving Behavior without Infractions via Amortized Inference »
Vasileios Lioutas · Adam Scibior · Frank Wood -
2022 : Physics aware inference for the cryo-EM inverse problem: anisotropic network model heterogeneity, global 3D pose and microscope defocus »
Geoffrey Woollard · Shayan Shekarforoush · Frank Wood · Marcus Brubaker · Khanh Dao Duc -
2023 Poster: A Diffusion-Model of Joint Interactive Navigation »
Matthew Niedoba · Jonathan Lavington · Yunpeng Liu · Vasileios Lioutas · Justice Sefas · Xiaoxuan Liang · Dylan Green · Setareh Dabiri · Berend Zwartsenberg · Adam Scibior · Frank Wood -
2022 Poster: BayesPCN: A Continually Learnable Predictive Coding Associative Memory »
Jinsoo Yoo · Frank Wood -
2022 Poster: Flexible Diffusion Modeling of Long Videos »
William Harvey · Saeid Naderiparizi · Vaden Masrani · Christian Weilbach · Frank Wood -
2020 Poster: Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective »
Vu Nguyen · Vaden Masrani · Rob Brekelmans · Michael A Osborne · Frank Wood -
2019 : Opening Remarks »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2019 Workshop: Machine Learning and the Physical Sciences »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2019 Poster: Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model »
Atilim Gunes Baydin · Lei Shao · Wahid Bhimji · Lukas Heinrich · Saeid Naderiparizi · Andreas Munk · Jialin Liu · Bradley Gram-Hansen · Gilles Louppe · Lawrence Meadows · Philip Torr · Victor Lee · Kyle Cranmer · Mr. Prabhat · Frank Wood -
2018 Poster: Faithful Inversion of Generative Models for Effective Amortized Inference »
Stefan Webb · Adam Golinski · Rob Zinkov · Siddharth N · Thomas Rainforth · Yee Whye Teh · Frank Wood -
2018 Poster: Bayesian Distributed Stochastic Gradient Descent »
Michael Teng · Frank Wood