Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Daniel Tarlow

Learning Generalized Gumbel-max Causal Mechanisms


Nov 11, 2021
Guy Lorberbom, Daniel D. Johnson, Chris J. Maddison, Daniel Tarlow, Tamir Hazan

* Accepted to NeurIPS 2021 (Spotlight) 

  Access Paper or Ask Questions

Beyond In-Place Corruption: Insertion and Deletion In Denoising Probabilistic Models


Jul 16, 2021
Daniel D. Johnson, Jacob Austin, Rianne van den Berg, Daniel Tarlow

* Accepted at the ICML 2021 Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (poster) 

  Access Paper or Ask Questions

Structured Denoising Diffusion Models in Discrete State-Spaces


Jul 13, 2021
Jacob Austin, Daniel D. Johnson, Jonathan Ho, Daniel Tarlow, Rianne van den Berg

* 10 pages plus references and appendices. First two authors contributed equally 

  Access Paper or Ask Questions

Learning to Combine Per-Example Solutions for Neural Program Synthesis


Jun 14, 2021
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow


  Access Paper or Ask Questions

Learning to Extend Program Graphs to Work-in-Progress Code


May 28, 2021
Xuechen Li, Chris J. Maddison, Daniel Tarlow


  Access Paper or Ask Questions

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks


Oct 23, 2020
David Bieber, Charles Sutton, Hugo Larochelle, Daniel Tarlow

* Accepted at NeurIPS 2020 

  Access Paper or Ask Questions

Software Engineering Event Modeling using Relative Time in Temporal Knowledge Graphs


Jul 13, 2020
Kian Ahrabian, Daniel Tarlow, Hehuimin Cheng, Jin L. C. Guo

* 11 pages, 1 figure. 37th International Conference on Machine Learning (ICML 2020) - Workshop on Graph Representation Learning and Beyond 

  Access Paper or Ask Questions

Learning Graph Structure With A Finite-State Automaton Layer


Jul 09, 2020
Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow

* Submitted to NeurIPS 2020 

  Access Paper or Ask Questions

Gradient Estimation with Stochastic Softmax Tricks


Jun 15, 2020
Max B. Paulus, Dami Choi, Daniel Tarlow, Andreas Krause, Chris J. Maddison


  Access Paper or Ask Questions

On-the-Fly Adaptation of Source Code Models using Meta-Learning


Mar 26, 2020
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow


  Access Paper or Ask Questions

Learning to Fix Build Errors with Graph2Diff Neural Networks


Nov 04, 2019
Daniel Tarlow, Subhodeep Moitra, Andrew Rice, Zimin Chen, Pierre-Antoine Manzagol, Charles Sutton, Edward Aftandilian

* Submitted for review on Aug 23, 2019 

  Access Paper or Ask Questions

Fast Training of Sparse Graph Neural Networks on Dense Hardware


Jun 27, 2019
Matej Balog, Bart van Merriënboer, Subhodeep Moitra, Yujia Li, Daniel Tarlow


  Access Paper or Ask Questions

Learning Execution through Neural Code Fusion


Jun 17, 2019
Zhan Shi, Kevin Swersky, Daniel Tarlow, Parthasarathy Ranganathan, Milad Hashemi

* 14 pages,7 figures 

  Access Paper or Ask Questions

Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces


Jun 14, 2019
Guy Lorberbom, Chris J. Maddison, Nicolas Heess, Tamir Hazan, Daniel Tarlow


  Access Paper or Ask Questions

Neural Networks for Modeling Source Code Edits


Apr 04, 2019
Rui Zhao, David Bieber, Kevin Swersky, Daniel Tarlow

* Deanonymized version of ICLR 2019 submission 

  Access Paper or Ask Questions

Graph Partition Neural Networks for Semi-Supervised Classification


Mar 16, 2018
Renjie Liao, Marc Brockschmidt, Daniel Tarlow, Alexander L. Gaunt, Raquel Urtasun, Richard Zemel


  Access Paper or Ask Questions

Gated Graph Sequence Neural Networks


Sep 22, 2017
Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel

* Published as a conference paper in ICLR 2016. Fixed a typo 

  Access Paper or Ask Questions

AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks


Jun 22, 2017
Alexander L. Gaunt, Matthew A. Johnson, Maik Riechert, Daniel Tarlow, Ryota Tomioka, Dimitrios Vytiniotis, Sam Webster

* 17 pages, 13 figures 

  Access Paper or Ask Questions

DeepCoder: Learning to Write Programs


Mar 08, 2017
Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow

* Submitted to ICLR 2017 

  Access Paper or Ask Questions

Differentiable Programs with Neural Libraries


Mar 02, 2017
Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow


  Access Paper or Ask Questions

Differentiable Functional Program Interpreters


Mar 02, 2017
John K. Feser, Marc Brockschmidt, Alexander L. Gaunt, Daniel Tarlow


  Access Paper or Ask Questions

Summary - TerpreT: A Probabilistic Programming Language for Program Induction


Dec 02, 2016
Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh, Nate Kushman, Pushmeet Kohli, Jonathan Taylor, Daniel Tarlow

* 7 pages, 2 figures, 4 tables in 1st Workshop on Neural Abstract Machines & Program Induction (NAMPI), @NIPS 2016 

  Access Paper or Ask Questions

TerpreT: A Probabilistic Programming Language for Program Induction


Aug 15, 2016
Alexander L. Gaunt, Marc Brockschmidt, Rishabh Singh, Nate Kushman, Pushmeet Kohli, Jonathan Taylor, Daniel Tarlow

* 50 pages, 20 figures, 4 tables 

  Access Paper or Ask Questions

Consensus Message Passing for Layered Graphical Models


Jan 26, 2015
Varun Jampani, S. M. Ali Eslami, Daniel Tarlow, Pushmeet Kohli, John Winn

* Appearing in Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (AISTATS) 2015 

  Access Paper or Ask Questions

A* Sampling


Jan 26, 2015
Chris J. Maddison, Daniel Tarlow, Tom Minka

* V2: - reworded the last paragraph of Section 2 to clarify that the argmax is a sample from the normalized measure. - fixed notation in Algorithm 1. - fixed a typo in paragraph 2 of Section 5 

  Access Paper or Ask Questions

Candidate Constrained CRFs for Loss-Aware Structured Prediction


Dec 10, 2014
Faruk Ahmed, Daniel Tarlow, Dhruv Batra

* 20 pages including Supplement 

  Access Paper or Ask Questions

Structured Generative Models of Natural Source Code


Jun 20, 2014
Chris J. Maddison, Daniel Tarlow


  Access Paper or Ask Questions

Detecting Parameter Symmetries in Probabilistic Models


Dec 19, 2013
Robert Nishihara, Thomas Minka, Daniel Tarlow

* 24 pages, 8 figures 

  Access Paper or Ask Questions

Tighter Linear Program Relaxations for High Order Graphical Models


Sep 26, 2013
Elad Mezuman, Daniel Tarlow, Amir Globerson, Yair Weiss

* Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013) 

  Access Paper or Ask Questions