Timezone: »
Variational inference (VI) and Markov chain Monte Carlo (MCMC) are approximate posterior inference algorithms that are often said to have complementary strengths, with VI being fast but biased and MCMC being slower but asymptotically unbiased. In this paper, we analyze gradient-based MCMC and VI procedures and find theoretical and empirical evidence that these procedures are not as different as one might think. In particular, a close examination of the Fokker-Planck equation that governs the Langevin dynamics (LD) MCMC procedure reveals that LD implicitly follows a gradient flow that corresponds to an VI procedure based on optimizing a nonparametric normalizing flow. The evolution under gradient descent of real-world VI approximations that use tractable, parametric flows can thus be seen as an approximation to the evolution of a population of LD-MCMC chains. This result suggests that the transient bias of LD (due to the Markov chain not having burned in) may track that of VI (due to the optimizer not having converged), up to differences due to VI’s asymptotic bias and parameter geometry. Empirically, we find that the transient biases of these algorithms (and their momentum-accelerated counterparts) do evolve similarly. This suggests that practitioners with a limited time budget may get more accurate results by running an MCMC procedure (even if it is stopped before fully burning in) than a VI procedure, as long as the variance of the MCMC estimator can be dealt with (e.g., by running many parallel chains).
Author Information
Matthew Hoffman (Google)
Yian Ma (Google)
More from the Same Authors
-
2021 Poster: What Are Bayesian Neural Network Posteriors Really Like? »
Pavel Izmailov · Sharad Vikram · Matthew Hoffman · Andrew Wilson -
2021 Oral: What Are Bayesian Neural Network Posteriors Really Like? »
Pavel Izmailov · Sharad Vikram · Matthew Hoffman · Andrew Wilson -
2020 Poster: On Thompson Sampling with Langevin Algorithms »
Eric Mazumdar · Aldo Pacchiano · Yian Ma · Michael Jordan · Peter Bartlett -
2020 Poster: Automatic Reparameterisation of Probabilistic Programs »
Maria Gorinova · Dave Moore · Matthew Hoffman -
2020 Poster: Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors »
Mike Dusenberry · Ghassen Jerfel · Yeming Wen · Yian Ma · Jasper Snoek · Katherine Heller · Balaji Lakshminarayanan · Dustin Tran -
2019 : Networking Lunch (provided) + Poster Session »
Abraham Stanway · Alex Robson · Aneesh Rangnekar · Ashesh Chattopadhyay · Ashley Pilipiszyn · Benjamin LeRoy · Bolong Cheng · Ce Zhang · Chaopeng Shen · Christian Schroeder · Christian Clough · Clement DUHART · Clement Fung · Cozmin Ududec · Dali Wang · David Dao · di wu · Dimitrios Giannakis · Dino Sejdinovic · Doina Precup · Duncan Watson-Parris · Gege Wen · George Chen · Gopal Erinjippurath · Haifeng Li · Han Zou · Herke van Hoof · Hillary A Scannell · Hiroshi Mamitsuka · Hongbao Zhang · Jaegul Choo · James Wang · James Requeima · Jessica Hwang · Jinfan Xu · Johan Mathe · Jonathan Binas · Joonseok Lee · Kalai Ramea · Kate Duffy · Kevin McCloskey · Kris Sankaran · Lester Mackey · Letif Mones · Loubna Benabbou · Lynn Kaack · Matthew Hoffman · Mayur Mudigonda · Mehrdad Mahdavi · Michael McCourt · Mingchao Jiang · Mohammad Mahdi Kamani · Neel Guha · Niccolo Dalmasso · Nick Pawlowski · Nikola Milojevic-Dupont · Paulo Orenstein · Pedram Hassanzadeh · Pekka Marttinen · Ramesh Nair · Sadegh Farhang · Samuel Kaski · Sandeep Manjanna · Sasha Luccioni · Shuby Deshpande · Soo Kim · Soukayna Mouatadid · Sunghyun Park · Tao Lin · Telmo Felgueira · Thomas Hornigold · Tianle Yuan · Tom Beucler · Tracy Cui · Volodymyr Kuleshov · Wei Yu · yang song · Ydo Wexler · Yoshua Bengio · Zhecheng Wang · Zhuangfang Yi · Zouheir Malki -
2017 Poster: Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo »
Matthew Hoffman -
2017 Talk: Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo »
Matthew Hoffman