PLUR: A Unifying, Graph-Based View of Program Learning, Understanding, and Repair

1 code implementation • NeurIPS 2021 • Zimin Chen, Vincent Hellendoorn, Pascal Lamblin, Petros Maniatis, Pierre-Antoine Manzagol, Daniel Tarlow, Subhodeep Moitra

Machine learning for understanding and editing source code has recently attracted significant interest, with many developments in new models, new code representations, and new tasks. This proliferation can appear disparate and disconnected, making each approach seemingly unique and incompatible, thus obscuring the core machine learning challenges and contributions. In this work, we demonstrate that the landscape can be significantly simplified by taking a general approach of mapping a graph to a sequence of tokens and pointers. Our main result is to show that 16 recently published tasks of different shapes can be cast in this form, based on which a single model architecture achieves near or above state-of-the-art results on nearly all tasks, outperforming custom models like code2seq and alternative generic models like Transformers. This unification further enables multi-task learning and a series of cross-cutting experiments about the importance of different modeling choices for code understanding and repair tasks. The full framework, called PLUR, is easily extensible to more tasks, and will be open-sourced (https://github. com/google-research/plur).

BIG-bench Machine Learning Multi-Task Learning

Learning to Fix Build Errors with Graph2Diff Neural Networks

no code implementations • 4 Nov 2019 • Daniel Tarlow, Subhodeep Moitra, Andrew Rice, Zimin Chen, Pierre-Antoine Manzagol, Charles Sutton, Edward Aftandilian

A diff specifies how to modify the code's abstract syntax tree, represented in the neural network as a sequence of tokens and of pointers to code locations.

Program Repair

Fast Training of Sparse Graph Neural Networks on Dense Hardware

no code implementations • 27 Jun 2019 • Matej Balog, Bart van Merriënboer, Subhodeep Moitra, Yujia Li, Daniel Tarlow

Graph neural networks have become increasingly popular in recent years due to their ability to naturally encode relational input data and their ability to scale to large graphs by operating on a sparse representation of graph adjacency matrices.

Distributional reinforcement learning with linear function approximation

no code implementations • 8 Feb 2019 • Marc G. Bellemare, Nicolas Le Roux, Pablo Samuel Castro, Subhodeep Moitra

Despite many algorithmic advances, our theoretical understanding of practical distributional reinforcement learning methods remains limited.

Distributional Reinforcement Learning reinforcement-learning +1

The Hanabi Challenge: A New Frontier for AI Research

1 code implementation • 1 Feb 2019 • Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare, Michael Bowling

From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making.

Decision Making Game of Hanabi

Dopamine: A Research Framework for Deep Reinforcement Learning

12 code implementations • 14 Dec 2018 • Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar, Marc G. Bellemare

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

reinforcement-learning Reinforcement Learning (RL)

Google Vizier: A Service for Black-Box Optimization

1 code implementation • ACM (2017) 2017 • Daniel Golovin, Benjamin Solnik, Subhodeep Moitra, Greg Kochanski, John Karro, D. Sculley

Any sufficiently complex system acts as a black box when it becomes easier to experiment with than to understand.

BIG-bench Machine Learning Hyperparameter Optimization +1