Timezone: »
Stochastic variational inference (SVI) lets us scale up Bayesian computation to massive data. It uses stochastic optimization to fit a variational distribution, following easy-to-compute noisy natural gradients. As with most traditional stochastic optimization methods, SVI takes precautions to use unbiased stochastic gradients whose expectations are equal to the true gradients. In this paper, we explore the idea of following biased stochastic gradients in SVI. Our method replaces the natural gradient with a similarly constructed vector that uses a fixed-window moving average of some of its previous terms. We will demonstrate the many advantages of this technique. First, its computational cost is the same as for SVI and storage requirements only multiply by a constant factor. Second, it enjoys significant variance reduction over the unbiased estimates, smaller bias than averaged gradients, and leads to smaller mean-squared error against the full gradient. We test our method on latent Dirichlet allocation with three large corpora.
Author Information
Stephan Mandt (University of California, Irvine)

Stephan Mandt is an Associate Professor of Computer Science and Statistics at the University of California, Irvine. From 2016 until 2018, he was a Senior Researcher and Head of the statistical machine learning group at Disney Research in Pittsburgh and Los Angeles. He held previous postdoctoral positions at Columbia University and Princeton University. Stephan holds a Ph.D. in Theoretical Physics from the University of Cologne, where he received the German National Merit Scholarship. He is furthermore a recipient of the NSF CAREER Award, the UCI ICS Mid-Career Excellence in Research Award, the German Research Foundation's Mercator Fellowship, a Kavli Fellow of the U.S. National Academy of Sciences, a member of the ELLIS Society, and a former visiting researcher at Google Brain. Stephan regularly serves as an Area Chair, Action Editor, or Editorial Board member for NeurIPS, ICML, AAAI, ICLR, TMLR, and JMLR. His research is currently supported by NSF, DARPA, DOE, Disney, Intel, and Qualcomm.
David Blei (Columbia University)
More from the Same Authors
-
2021 : Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs »
Harshini Mangipudi · Griffin Mooers · Mike Pritchard · Tom Beucler · Stephan Mandt -
2021 : Structured Stochastic Gradient MCMC: a hybrid VI and MCMC approach »
Antonios Alexos · Alex Boyd · Stephan Mandt -
2022 : Probabilistic Querying of Continuous-Time Sequential Events »
Alex Boyd · Yuxin Chang · Stephan Mandt · Padhraic Smyth -
2022 : An Unsupervised Learning Perspective on the Dynamic Contribution to Extreme Precipitation Changes »
Griffin Mooers · Tom Beucler · Mike Pritchard · Stephan Mandt -
2023 Workshop: Deep Generative Models for Health »
Emanuele Palumbo · Laura Manduchi · Sonia Laguna · Melanie F. Pradier · Vincent Fortuin · Stephan Mandt · Julia Vogt -
2022 : Q & A »
Karen Ullrich · Yibo Yang · Stephan Mandt -
2022 Tutorial: Data Compression with Machine Learning »
Karen Ullrich · Yibo Yang · Stephan Mandt -
2022 : Tutorial part 1 »
Yibo Yang · Karen Ullrich · Stephan Mandt -
2022 Poster: Predictive Querying for Autoregressive Neural Sequence Models »
Alex Boyd · Samuel Showalter · Stephan Mandt · Padhraic Smyth -
2021 Poster: Detecting and Adapting to Irregular Distribution Shifts in Bayesian Online Learning »
Aodong Li · Alex Boyd · Padhraic Smyth · Stephan Mandt -
2020 : Q/A and Discussion for ML Theory Session »
Karthik Kashinath · Mayur Mudigonda · Stephan Mandt · Rose Yu -
2020 : Stephan Mandt »
Stephan Mandt -
2020 Poster: User-Dependent Neural Sequence Models for Continuous-Time Event Data »
Alex Boyd · Robert Bamler · Stephan Mandt · Padhraic Smyth -
2020 Poster: Improving Inference for Neural Image Compression »
Yibo Yang · Robert Bamler · Stephan Mandt -
2019 Poster: Deep Generative Video Compression »
Salvator Lombardo · JUN HAN · Christopher Schroers · Stephan Mandt -
2017 : Introduction »
Cheng Zhang · Francisco Ruiz · Dustin Tran · James McInerney · Stephan Mandt -
2017 Workshop: Advances in Approximate Bayesian Inference »
Francisco Ruiz · Stephan Mandt · Cheng Zhang · James McInerney · James McInerney · Dustin Tran · Dustin Tran · David Blei · Max Welling · Tamara Broderick · Michalis Titsias -
2017 Poster: Perturbative Black Box Variational Inference »
Robert Bamler · Cheng Zhang · Manfred Opper · Stephan Mandt -
2016 Workshop: Advances in Approximate Bayesian Inference »
Tamara Broderick · Stephan Mandt · James McInerney · Dustin Tran · David Blei · Kevin Murphy · Andrew Gelman · Michael I Jordan -
2016 Poster: Exponential Family Embeddings »
Maja Rudolph · Francisco Ruiz · Stephan Mandt · David Blei -
2015 : Finding Sparse Features in Strongly Confounded Medial Data »
Stephan Mandt · Florian Wenzel -
2015 Workshop: Advances in Approximate Bayesian Inference »
Dustin Tran · Tamara Broderick · Stephan Mandt · James McInerney · Shakir Mohamed · Alp Kucukelbir · Matthew D. Hoffman · Neil Lawrence · David Blei -
2014 Workshop: Advances in Variational Inference »
David Blei · Shakir Mohamed · Michael Jordan · Charles Blundell · Tamara Broderick · Matthew D. Hoffman -
2014 Poster: A Filtering Approach to Stochastic Variational Inference »
Neil Houlsby · David Blei -
2014 Poster: Content-based recommendations with Poisson factorization »
Prem Gopalan · Laurent Charlin · David Blei -
2013 Workshop: Topic Models: Computation, Application, and Evaluation »
David Mimno · Amr Ahmed · Jordan Boyd-Graber · Ankur Moitra · Hanna Wallach · Alexander Smola · David Blei · Anima Anandkumar -
2013 Workshop: Probabilistic Models for Big Data »
Neil D Lawrence · Joaquin QuiƱonero-Candela · Tianshi Gao · James Hensman · Zoubin Ghahramani · Max Welling · David Blei · Ralf Herbrich -
2013 Poster: Efficient Online Inference for Bayesian Nonparametric Relational Models »
Dae Il Kim · Prem Gopalan · David Blei · Erik Sudderth -
2013 Poster: Modeling Overlapping Communities with Node Popularities »
Prem Gopalan · Chong Wang · David Blei -
2012 Poster: Truncation-free Online Variational Inference for Bayesian Nonparametric Models »
Chong Wang · David Blei -
2012 Poster: Scalable Inference of Overlapping Communities »
Prem Gopalan · David Mimno · Sean Gerrish · Michael Freedman · David Blei -
2012 Spotlight: Scalable Inference of Overlapping Communities »
Prem Gopalan · David Mimno · Sean Gerrish · Michael Freedman · David Blei -
2012 Poster: How They Vote: Issue-Adjusted Models of Legislative Behavior »
Sean Gerrish · David Blei -
2011 Poster: Spatial distance dependent Chinese Restaurant Process for image segmentation »
Soumya Ghosh · Andrei B Ungureanu · Erik Sudderth · David Blei -
2010 Session: Oral Session 18 »
David Blei -
2010 Spotlight: Online Learning for Latent Dirichlet Allocation »
Matthew D. Hoffman · David Blei · Francis Bach -
2010 Poster: Online Learning for Latent Dirichlet Allocation »
Matthew D. Hoffman · David Blei · Francis Bach -
2010 Poster: Nonparametric Density Estimation for Stochastic Optimization with an Observable State Variable »
Lauren A Hannah · Warren B Powell · David Blei -
2009 Workshop: Applications for Topic Models: Text and Beyond »
David Blei · Jordan Boyd-Graber · Jonathan Chang · Katherine Heller · Hanna Wallach -
2009 Poster: Reading Tea Leaves: How Humans Interpret Topic Models »
Jonathan Chang · Jordan Boyd-Graber · Sean Gerrish · Chong Wang · David Blei -
2009 Oral: Reading Tea Leaves: How Humans Interpret Topic Models »
Jonathan Chang · Jordan Boyd-Graber · Sean Gerrish · Chong Wang · David Blei -
2009 Poster: Decoupling Sparsity and Smoothness in the Discrete Hierarchical Dirichlet Process »
Chong Wang · David Blei -
2009 Spotlight: Decoupling Sparsity and Smoothness in the Discrete Hierarchical Dirichlet Process »
Chong Wang · David Blei -
2009 Poster: Variational Inference for the Nested Chinese Restaurant Process »
Chong Wang · David Blei -
2009 Poster: A Bayesian Analysis of Dynamics in Free Recall »
Richard Socher · Samuel J Gershman · Adler Perotte · Per Sederberg · David Blei · Kenneth Norman -
2008 Workshop: Analyzing Graphs: Theory and Applications »
Edo M Airoldi · David Blei · Jake M Hofman · Tony Jebara · Eric Xing -
2008 Poster: Mixed Membership Stochastic Blockmodels »
Edo M Airoldi · David Blei · Stephen E Fienberg · Eric Xing -
2008 Spotlight: Mixed Membership Stochastic Blockmodels »
Edo M Airoldi · David Blei · Stephen E Fienberg · Eric Xing -
2008 Poster: Syntactic Topic Models »
Jordan Boyd-Graber · David Blei -
2008 Poster: Relative Performance Guarantees for Approximate Inference in Latent Dirichlet Allocation »
Indraneel Mukherjee · David Blei -
2008 Spotlight: Syntactic Topic Models »
Jordan Boyd-Graber · David Blei -
2008 Spotlight: Relative Performance Guarantees for Approximate Inference in Latent Dirichlet Allocation »
Indraneel Mukherjee · David Blei -
2007 Poster: Supervised Topic Models »
David Blei · Jon McAuliffe