Mila > Team > Danny Tarlow

Danny Tarlow

Core Industry Member
Adjunct Professor, McGill University, Google

Danny Tarlow is a research scientist at Google Brain. His main interest is in automatic learning methods for understanding and generating programs. He is also an adjunct professor at the School of Computer Science at McGill University. He holds a PhD from the Automatic Learning Group at the University of Toronto and spent four years as a post-doctoral fellow and then as a researcher at Microsoft Research in Cambridge before moving to Montreal.

Publications

2021-12

Learning Generalized Gumbel-max Causal Mechanisms
Guy Lorberbom, Daniel D. Johnson, Chris J. Maddison, Daniel Tarlow and Tamir Hazan
PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair
Zimin Chen, Vincent Hellendoorn, Pascal Lamblin, Petros Maniatis, Pierre-Antoine Manzagol, Daniel Tarlow and Subhodeep Moitra
NEURIPS 2021
(2021-12-06)
papers.nips.ccPDF
Structured Denoising Diffusion Models in Discrete State-Spaces
Jacob Austin, Daniel Dun-ning Woo Johnson, Jonathan Ho, Danny Tarlow and Rianne van den Berg
Learning to Combine Per-Example Solutions for Neural Program Synthesis
Disha Shrivastava, Hugo Larochelle and Daniel Tarlow

2021-06

Beyond In-Place Corruption: Insertion and Deletion In Denoising Probabilistic Models
Daniel D. Johnson, Jacob Austin, Rianne van den Berg and Daniel Tarlow

2021-05

Learning to Extend Program Graphs to Work-in-Progress Code.
Xuechen Li, Chris J. Maddison and Daniel Tarlow
arXiv preprint arXiv:2105.14038
(2021-05-28)
ui.adsabs.harvard.eduPDF

2020-12

Tabular: Probabilistic Inference from the Spreadsheet
Andrew D. Gordon, Claudio Russo, Marcin Szymczak, Johannes Borgström, Nicolas Rolland, Thore Graepel and Daniel Tarlow
(venue unknown)
(2020-12-01)
www.cambridge.org

2020-11

OPTIMIZING SPARSE GRAPH NEURAL NETWORKS FOR DENSE HARDWARE
Tarlow Daniel S, Balog Matej, Van Merrienboer Bart, Li Yujia and Moitra Subhodeep
(venue unknown)
(2020-11-26)
lens.org

2020-07

Learning Graph Structure With A Finite-State Automaton Layer
Daniel D. Johnson, Hugo Larochelle and Daniel Tarlow
Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs.
Kian Ahrabian, Daniel Tarlow, Hehuimin Cheng and Jin L. C. Guo
arXiv preprint arXiv:2007.01231
(2020-07-02)
ui.adsabs.harvard.eduPDF

2020-06

Learning to Fix Build Errors with Graph2Diff Neural Networks
Daniel Tarlow, Subhodeep Moitra, Andrew Rice, Zimin Chen, Pierre-Antoine Manzagol, Charles Sutton and Edward Aftandilian
Gradient Estimation with Stochastic Softmax Tricks
Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause and Chris J. Maddison

2020-04

LEARNING EXECUTION THROUGH NEURAL CODE FUSION
Zhan Shi, Kevin Swersky, Daniel Tarlow, Parthasarathy Ranganathan and Milad Hashemi

2020-03

On-the-Fly Adaptation of Source Code Models using Meta-Learning
Disha Shrivastava, Hugo Larochelle and Daniel Tarlow
arXiv: Learning
(2020-03-26)
ui.adsabs.harvard.eduPDF

2020-01

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
David Bieber, Charles Sutton, Hugo Larochelle and Daniel Tarlow
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
Guy Lorberbom, Chris J. Maddison, Nicolas Heess, Tamir Hazan and Daniel Tarlow

2019-09

Fast Training of Sparse Graph Neural Networks on Dense Hardware
Matej Balog, Bart van Merriënboer, Subhodeep Moitra, Yujia Li and Daniel Tarlow
arXiv: Machine Learning
(2019-09-25)
ui.adsabs.harvard.eduPDF

Publications collected and formatted using Paperoni