Matthew J. Johnson

Publication Activity (10 Years)

Years Active: 2010-2023
Publications (10 Years): 23

Top Topics

Linear Dynamical Systems

Unsupervised Learning

Structured Representations

Bayesian Nonparametric

Top Venues

Publications

Alexey Radul, Adam Paszke, Roy Frostig, Matthew J. Johnson, Dougal Maclaurin
You Only Linearize Once: Tangents Transpose to Gradients. Proc. ACM Program. Lang. 7 (POPL) (2023)
Aidan Clark, Diego de Las Casas, Aurelia Guy, Arthur Mensch, Michela Paganini, Jordan Hoffmann, Bogdan Damoc, Blake A. Hechtman, Trevor Cai, Sebastian Borgeaud, George van den Driessche, Eliza Rutherford, Tom Hennigan, Matthew J. Johnson, Albin Cassirer, Chris Jones, Elena Buchatskaya, David Budden, Laurent Sifre, Simon Osindero, Oriol Vinyals, Marc'Aurelio Ranzato, Jack W. Rae, Erich Elsen, Koray Kavukcuoglu, Karen Simonyan
Unified Scaling Laws for Routed Language Models. ICML (2022)
Alexey Radul, Adam Paszke, Roy Frostig, Matthew J. Johnson, Dougal Maclaurin
You Only Linearize Once: Tangents Transpose to Gradients. CoRR (2022)
Adam Paszke, Daniel D. Johnson, David Duvenaud, Dimitrios Vytiniotis, Alexey Radul, Matthew J. Johnson, Jonathan Ragan-Kelley, Dougal Maclaurin
Getting to the point: index sets and parallelism-preserving autodiff for pointful array programming. Proc. ACM Program. Lang. 5 (POPL) (2021)
Adam Paszke, Matthew J. Johnson, Roy Frostig, Dougal Maclaurin
Parallelism-preserving automatic differentiation for second-order array languages. FHPNC@ICFP (2021)
Adam Paszke, Daniel D. Johnson, David Duvenaud, Dimitrios Vytiniotis, Alexey Radul, Matthew J. Johnson, Jonathan Ragan-Kelley, Dougal Maclaurin
Getting to the Point. Index Sets and Parallelism-Preserving Autodiff for Pointful Array Programming. CoRR (2021)
Roy Frostig, Matthew J. Johnson, Dougal Maclaurin, Adam Paszke, Alexey Radul
Decomposing reverse-mode automatic differentiation. CoRR (2021)
Jacob Kelly, Jesse Bettencourt, Matthew J. Johnson, David Duvenaud
Learning Differential Equations that are Easy to Solve. NeurIPS (2020)
Marvin Zhang, Sharad Vikram, Laura Smith, Pieter Abbeel, Matthew J. Johnson, Sergey Levine
SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning. ICML (2019)
Sharad Vikram, Matthew D. Hoffman, Matthew J. Johnson
The LORACs Prior for VAEs: Letting the Trees Speak for the Data. AISTATS (2019)
Sharad Vikram, Matthew D. Hoffman, Matthew J. Johnson
The LORACs prior for VAEs: Letting the Trees Speak for the Data. CoRR (2018)
Dustin Tran, Matthew D. Hoffman, Dave Moore, Christopher Suter, Srinivas Vasudevan, Alexey Radul, Matthew J. Johnson, Rif A. Saurous
Simple, Distributed, and Accelerated Probabilistic Programming. CoRR (2018)
Marvin Zhang, Sharad Vikram, Laura Smith, Pieter Abbeel, Matthew J. Johnson, Sergey Levine
SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning. CoRR (2018)
Ardavan Saeedi, Matthew D. Hoffman, Stephen J. DiVerdi, Asma Ghandeharioun, Matthew J. Johnson, Ryan P. Adams
Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models. AISTATS (2018)
Matthew D. Hoffman, Matthew J. Johnson, Dustin Tran
Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language. CoRR (2018)
Scott W. Linderman, Matthew J. Johnson, Andrew C. Miller, Ryan P. Adams, David M. Blei, Liam Paninski
Bayesian Learning and Inference in Recurrent Switching Linear Dynamical Systems. AISTATS (2017)
Scott W. Linderman, Matthew J. Johnson
Structure-Exploiting variational inference for recurrent switching linear dynamical systems. CAMSAP (2017)
Ardavan Saeedi, Matthew D. Hoffman, Stephen J. DiVerdi, Asma Ghandeharioun, Matthew J. Johnson, Ryan P. Adams
Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models. CoRR (2017)
Huseyin Melih Elibol, Vincent Nguyen, Scott W. Linderman, Matthew J. Johnson, Amna Hashmi, Finale Doshi-Velez
Cross-Corpora Unsupervised Learning of Trajectories in Autism Spectrum Disorders. J. Mach. Learn. Res. 17 (2016)
Matthew J. Johnson, David Duvenaud, Alexander B. Wiltschko, Ryan P. Adams, Sandeep R. Datta
Composing graphical models with neural networks for structured representations and fast inference. NIPS (2016)
Ardavan Saeedi, Matthew D. Hoffman, Matthew J. Johnson, Ryan P. Adams
The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM. ICML (2016)
Scott W. Linderman, Matthew J. Johnson, Ryan P. Adams
Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation. NIPS (2015)
Jonathan H. Huggins, Ardavan Saeedi, Matthew J. Johnson
Detailed Derivations of Small-Variance Asymptotics for some Hierarchical Bayesian Nonparametric Models. CoRR (2015)
Matthew J. Johnson, James Saunderson, Alan S. Willsky
Analyzing Hogwild Parallel Gaussian Gibbs Sampling. NIPS (2013)
Matthew J. Johnson, Alan S. Willsky
Bayesian nonparametric hidden semi-Markov models. J. Mach. Learn. Res. 14 (1) (2013)
Matthew J. Johnson, Alan S. Willsky
The Hierarchical Dirichlet Process Hidden Semi-Markov Model CoRR (2012)
Vincent Y. F. Tan, Matthew J. Johnson, Alan S. Willsky
Necessary and sufficient conditions for high-dimensional salient feature subset recovery. ISIT (2010)
Matthew J. Johnson, Alan S. Willsky
The Hierarchical Dirichlet Process Hidden Semi-Markov Model. UAI (2010)