Matthew J. Johnson

30 papers A* 4A 4B 1Journal 16Unranked 5

Year	Rank	Type	Title / Venue / Authors
2023	J	`jnl`	You Only Linearize Once: Tangents Transpose to Gradients. Proc. ACM Program. Lang. Alexey Radul, Adam Paszke, Roy Frostig, Matthew J. Johnson, Dougal Maclaurin
2022	A*	`conf`	Unified Scaling Laws for Routed Language Models. ICML 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
2022	J	`jnl`	Unified Scaling Laws for Routed Language Models. CoRR 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, Katie Millican, Albin Cassirer, Chris Jones, Elena Buchatskaya, David Budden, Laurent Sifre, Simon Osindero, Oriol Vinyals, Jack W. Rae, Erich Elsen, Koray Kavukcuoglu, Karen Simonyan
2022	J	`jnl`	You Only Linearize Once: Tangents Transpose to Gradients. CoRR Alexey Radul, Adam Paszke, Roy Frostig, Matthew J. Johnson, Dougal Maclaurin
2021	J	`jnl`	Decomposing reverse-mode automatic differentiation. CoRR Roy Frostig, Matthew J. Johnson, Dougal Maclaurin, Adam Paszke, Alexey Radul
2021	J	`jnl`	Getting to the Point. Index Sets and Parallelism-Preserving Autodiff for Pointful Array Programming. CoRR Adam Paszke, Daniel D. Johnson, David Duvenaud, Dimitrios Vytiniotis, Alexey Radul, Matthew J. Johnson, Jonathan Ragan-Kelley, Dougal Maclaurin
2021	J	`jnl`	Getting to the point: index sets and parallelism-preserving autodiff for pointful array programming. Proc. ACM Program. Lang. Adam Paszke, Daniel D. Johnson, David Duvenaud, Dimitrios Vytiniotis, Alexey Radul, Matthew J. Johnson, Jonathan Ragan-Kelley, Dougal Maclaurin
2021	—	`conf`	Parallelism-preserving automatic differentiation for second-order array languages. FHPNC@ICFP Adam Paszke, Matthew J. Johnson, Roy Frostig, Dougal Maclaurin
2021	J	`jnl`	Scaling Language Models: Methods, Analysis & Insights from Training Gopher. CoRR Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, H. Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Erich Elsen, Siddhant M. Jayakumar, Elena Buchatskaya, David Budden, Esme Sutherland, Karen Simonyan, Michela Paganini, Laurent Sifre, Lena Martens, Xiang Lorraine Li, Adhiguna Kuncoro, Aida Nematzadeh, Elena Gribovskaya, Domenic Donato, Angeliki Lazaridou, Arthur Mensch, Jean-Baptiste Lespiau, Maria Tsimpoukelli, Nikolai Grigorev, Doug Fritz, Thibault Sottiaux, Mantas Pajarskas, Toby Pohlen, Zhitao Gong, Daniel Toyama, Cyprien de Masson d'Autume, Yujia Li, Tayfun Terzi, Vladimir Mikulik, Igor Babuschkin, Aidan Clark, Diego de Las Casas, Aurelia Guy, Chris Jones, James Bradbury, Matthew J. Johnson, Blake A. Hechtman, Laura Weidinger, Iason Gabriel, William Isaac, Edward Lockhart, Simon Osindero, Laura Rimell, Chris Dyer, Oriol Vinyals, Kareem Ayoub, Jeff Stanway, Lorrayne Bennett, Demis Hassabis, Koray Kavukcuoglu, Geoffrey Irving
2020	A*	`conf`	Learning Differential Equations that are Easy to Solve. NeurIPS Jacob Kelly, Jesse Bettencourt, Matthew J. Johnson, David Duvenaud
2019	A*	`conf`	SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning. ICML Marvin Zhang, Sharad Vikram, Laura Smith, Pieter Abbeel, Matthew J. Johnson, Sergey Levine
2019	A	`conf`	The LORACs Prior for VAEs: Letting the Trees Speak for the Data. AISTATS Sharad Vikram, Matthew D. Hoffman, Matthew J. Johnson
2018	J	`jnl`	Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language. CoRR Matthew D. Hoffman, Matthew J. Johnson, Dustin Tran
2018	A	`conf`	Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models. AISTATS Ardavan Saeedi, Matthew D. Hoffman, Stephen J. DiVerdi, Asma Ghandeharioun, Matthew J. Johnson, Ryan P. Adams
2018	J	`jnl`	SOLAR: Deep Structured Latent Representations for Model-Based Reinforcement Learning. CoRR Marvin Zhang, Sharad Vikram, Laura Smith, Pieter Abbeel, Matthew J. Johnson, Sergey Levine
2018	J	`jnl`	Simple, Distributed, and Accelerated Probabilistic Programming. CoRR Dustin Tran, Matthew D. Hoffman, Dave Moore, Christopher Suter, Srinivas Vasudevan, Alexey Radul, Matthew J. Johnson, Rif A. Saurous
2018	J	`jnl`	The LORACs prior for VAEs: Letting the Trees Speak for the Data. CoRR Sharad Vikram, Matthew D. Hoffman, Matthew J. Johnson
2017	A	`conf`	Bayesian Learning and Inference in Recurrent Switching Linear Dynamical Systems. AISTATS Scott W. Linderman, Matthew J. Johnson, Andrew C. Miller, Ryan P. Adams, David M. Blei, Liam Paninski
2017	J	`jnl`	Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models. CoRR Ardavan Saeedi, Matthew D. Hoffman, Stephen J. DiVerdi, Asma Ghandeharioun, Matthew J. Johnson, Ryan P. Adams
2017	—	`conf`	Structure-Exploiting variational inference for recurrent switching linear dynamical systems. CAMSAP Scott W. Linderman, Matthew J. Johnson
2016	—	`conf`	Composing graphical models with neural networks for structured representations and fast inference. NIPS Matthew J. Johnson, David Duvenaud, Alexander B. Wiltschko, Ryan P. Adams, Sandeep R. Datta
2016	J	`jnl`	Cross-Corpora Unsupervised Learning of Trajectories in Autism Spectrum Disorders. J. Mach. Learn. Res. Huseyin Melih Elibol, Vincent Nguyen, Scott W. Linderman, Matthew J. Johnson, Amna Hashmi, Finale Doshi-Velez
2016	A*	`conf`	The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM. ICML Ardavan Saeedi, Matthew D. Hoffman, Matthew J. Johnson, Ryan P. Adams
2015	—	`conf`	Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation. NIPS Scott W. Linderman, Matthew J. Johnson, Ryan P. Adams
2015	J	`jnl`	Detailed Derivations of Small-Variance Asymptotics for some Hierarchical Bayesian Nonparametric Models. CoRR Jonathan H. Huggins, Ardavan Saeedi, Matthew J. Johnson
2013	—	`conf`	Analyzing Hogwild Parallel Gaussian Gibbs Sampling. NIPS Matthew J. Johnson, James Saunderson, Alan S. Willsky
2013	J	`jnl`	Bayesian nonparametric hidden semi-Markov models. J. Mach. Learn. Res. Matthew J. Johnson, Alan S. Willsky
2012	J	`jnl`	The Hierarchical Dirichlet Process Hidden Semi-Markov Model CoRR Matthew J. Johnson, Alan S. Willsky
2010	B	`conf`	Necessary and sufficient conditions for high-dimensional salient feature subset recovery. ISIT Vincent Y. F. Tan, Matthew J. Johnson, Alan S. Willsky
2010	A	`conf`	The Hierarchical Dirichlet Process Hidden Semi-Markov Model. UAI Matthew J. Johnson, Alan S. Willsky