
Couplings for Multinomial Hamiltonian Monte Carlo
Hamiltonian Monte Carlo (HMC) is a popular sampling method in Bayesian i...
read it

Latent Programmer: Discrete Latent Codes for Program Synthesis
In many sequence learning tasks, such as program synthesis and document ...
read it

Learning Discrete Energybased Models via Auxiliaryvariable Local Exploration
Discrete structures play an important role in applications like program ...
read it

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
Graph neural networks (GNNs) have emerged as a powerful tool for learnin...
read it

Conditional independence by typing
A central goal of probabilistic programming languages (PPLs) is to separ...
read it

BUSTLE: Bottomup programSynthesis Through Learningguided Exploration
Program synthesis is challenging largely because of the difficulty of se...
read it

Neural Program Synthesis with a Differentiable Fixer
We present a new program synthesis approach that combines an encoderdec...
read it

SCELMo: Source Code Embeddings from Language Models
Continuous embeddings of tokens in computer programs have been used to s...
read it

OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
We present a new approach to the type inference problem for dynamic lang...
read it

Big Code != Big Vocabulary: OpenVocabulary Models for Source Code
Statistical language modeling techniques have successfully been applied ...
read it

Towards Modular Algorithm Induction
We present a modular neural network architecture Main that learns algori...
read it

Incremental Sampling Without Replacement for Sequence Models
Sampling is a fundamental technique, and sampling without replacement is...
read it

Learning to Represent Programs with Property Signatures
We introduce the notion of property signatures, a representation for pro...
read it

Learning to Fix Build Errors with Graph2Diff Neural Networks
Professional software developers spend a significant amount of time fixi...
read it

Robust Variational Autoencoders for Outlier Detection in MixedType Data
We focus on the problem of unsupervised cell outlier detection in mixed ...
read it

How Often Do SingleStatement Bugs Occur? The ManySStuBs4J Dataset
Program repair is an important but difficult software engineering proble...
read it

Learning Semantic Annotations for Tabular Data
The usefulness of tabular data such as web tables critically depends on ...
read it

Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
Statistical language modeling techniques have successfully been applied ...
read it

Wrangling Messy CSV Files by Detecting Row and Type Patterns
It is well known that data scientists spend the majority of their time o...
read it

ColNet: Embedding the Semantics of Web Tables for Column Type Prediction
Automatically annotating column types with knowledge base (KB) concepts ...
read it

Probabilistic Programming with Densities in SlicStan: Efficient, Flexible and Deterministic
Stan is a probabilistic programming language that has been increasingly ...
read it

Deep Learning to Detect Redundant Method Comments
Comments in software are critical for maintenance and reuse. But apart f...
read it

Ratio Matching MMD Nets: Low dimensional projections for effective deep generative models
Deep generative models can learn to generate realisticlooking images on...
read it

Variational Inference In Pachinko Allocation Machines
The Pachinko Allocation Machine (PAM) is a deep topic model that allows ...
read it

Synthesis of Differentiable Functional Programs for Lifelong Learning
We present a neurosymbolic approach to the lifelong learning of algorith...
read it

Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
Interpreting black box classifiers, such as deep networks, allows an ana...
read it

Popularity of arXiv.org within Computer Science
It may seem surprising that, out of all areas of science, computer scien...
read it

A Survey of Machine Learning for Big Code and Naturalness
Research at the intersection of machine learning, programming languages,...
read it

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Deep generative models provide powerful tools for distributions over com...
read it

Autoencoding Variational Inference For Topic Models
Topic models are one of the most popular methods for learning representa...
read it

Learning Continuous Semantic Representations of Symbolic Expressions
Combining abstract, symbolic reasoning with continuous neural reasoning ...
read it

Clustering with a Reject Option: Interactive Clustering as Bayesian Prior Elicitation
A good clustering can help a data analyst to explore and understand a da...
read it

A Subsequence Interleaving Model for Sequential Pattern Mining
Recent sequential pattern mining methods have used the minimum descripti...
read it

A Convolutional Attention Network for Extreme Summarization of Source Code
Attention mechanisms in neural networks have proved useful for problems ...
read it

Latent Bayesian melding for integrating individual and population models
In many statistical problems, a more coarsegrained model may be suitabl...
read it

A Bayesian Network Model for Interesting Itemsets
Mining itemsets that are the most interesting under a statistical model ...
read it

SemiSeparable Hamiltonian Monte Carlo for Inference in Bayesian Hierarchical Models
Sampling from hierarchical Bayesian models is often difficult for MCMC m...
read it

Piecewise Training for Undirected Models
For many large undirected models that arise in realworld applications, ...
read it

Improved Dynamic Schedules for Belief Propagation
Belief propagation and its variants are popular methods for approximate ...
read it

An Introduction to Conditional Random Fields
Often we wish to predict a large number of variables that depend on each...
read it

Bayesian inference for queueing networks and modeling of internet services
Modern Internet services, such as those at Google, Yahoo!, and Amazon, h...
read it
Charles Sutton
is this you? claim profile
Machine learning, natural language processing, computer systems applications of machine learning. Graphical modelling, approximate inference.