Chris J. Maddison

research

∙ 08/08/2023

Probabilistic Invariant Learning with Randomized Linear Classifiers

Designing models that are both expressive and preserve known invariances...

0 Leonardo Cotta, et al. ∙

research

∙ 06/12/2023

Benchmarking Neural Network Training Algorithms

Training algorithms, broadly construed, are an essential part of every d...

6 George E. Dahl, et al. ∙

research

∙ 10/04/2022

Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions

Contrastive learning is a powerful framework for learning self-supervise...

0 Daniel D. Johnson, et al. ∙

research

∙ 06/27/2022

Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learning

Cutting planes are essential for solving mixed-integer linear problems (...

2 Max B. Paulus, et al. ∙

research

∙ 03/04/2022

The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights

Combinatorial optimization is a well-established area in operations rese...

12 Maxime Gasse, et al. ∙

research

∙ 02/17/2022

Augment with Care: Contrastive Learning for the Boolean Satisfiability Problem

Supervised learning can improve the design of state-of-the-art solvers f...

3 Haonan Duan, et al. ∙

research

∙ 02/09/2022

Bayesian Nonparametrics for Offline Skill Discovery

Skills or low-level policies in reinforcement learning are temporally ex...

0 Valentin Villecroze, et al. ∙

research

∙ 11/11/2021

Learning Generalized Gumbel-max Causal Mechanisms

To perform counterfactual reasoning in Structural Causal Models (SCMs), ...

0 Guy Lorberbom, et al. ∙

research

∙ 09/24/2021

Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts

Training large-scale mixture of experts models efficiently on modern har...

0 Wouter Kool, et al. ∙

research

∙ 06/21/2021

Lossy Compression for Lossless Prediction

Most data is automatically collected and only ever "seen" by algorithms....

12 Yann Dubois, et al. ∙

research

∙ 05/28/2021

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

Source code spends most of its time in a broken or incomplete state duri...

0 Xuechen Li, et al. ∙

research

∙ 02/22/2021

Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding

Latent variable models have been successfully applied in lossless compre...

0 Yangjun Ruan, et al. ∙

research

∙ 02/08/2021

Oops I Took A Gradient: Scalable Sampling for Discrete Distributions

We propose a general and scalable approximate sampling strategy for prob...

2 Will Grathwohl, et al. ∙

research

∙ 10/09/2020

Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient Estimator

Gradient estimation in models with discrete latent variables is a challe...

8 Max B. Paulus, et al. ∙

research

∙ 07/07/2020

Learning Branching Heuristics for Propositional Model Counting

Propositional model counting or #SAT is the problem of computing the num...

8 Pashootan Vaezipoor, et al. ∙

research

∙ 06/15/2020

Gradient Estimation with Stochastic Softmax Tricks

The Gumbel-Max trick is the basis of many relaxed gradient estimators. T...

0 Max B. Paulus, et al. ∙

research

∙ 10/11/2019

On Empirical Comparisons of Optimizers for Deep Learning

Selecting an optimizer is a central step in the contemporary deep learni...

0 Dami Choi, et al. ∙

research

∙ 06/14/2019

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

Direct optimization is an appealing approach to differentiating through ...

3 Guy Lorberbom, et al. ∙

research

∙ 01/17/2019

Hierarchical Representations with Poincaré Variational Auto-Encoders

The Variational Auto-Encoder (VAE) model has become widely popular as a ...

0 Emile Mathieu, et al. ∙

research

∙ 10/09/2018

Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives

Deep latent variable models have become a popular model choice due to th...

18 George Tucker, et al. ∙

research

∙ 09/13/2018

Hamiltonian Descent Methods

We propose a family of optimization methods that achieve linear converge...

0 Chris J. Maddison, et al. ∙

research

∙ 07/04/2018

Conditional Neural Processes

Deep neural networks excel at function approximation, yet they are typic...

2 Marta Garnelo, et al. ∙

research

∙ 02/13/2018

Tighter Variational Bounds are Not Necessarily Better

We provide theoretical and empirical evidence that using tighter evidenc...

0 Tom Rainforth, et al. ∙

research

∙ 05/25/2017

Filtering Variational Objectives

When used as a surrogate objective for maximum likelihood estimation in ...

0 Chris J. Maddison, et al. ∙

research

∙ 03/21/2017

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

Learning in models with discrete latent variables is challenging due to ...

0 George Tucker, et al. ∙

research

∙ 11/02/2016

The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

The reparameterization trick enables optimizing large scale stochastic c...

0 Chris J. Maddison, et al. ∙

research

∙ 12/20/2014

Move Evaluation in Go Using Deep Convolutional Neural Networks

The game of Go is more challenging than other board games, due to the di...

0 Chris J. Maddison, et al. ∙

research

∙ 10/31/2014

A* Sampling

The problem of drawing samples from a discrete distribution can be conve...

0 Chris J. Maddison, et al. ∙

research

∙ 01/02/2014

Structured Generative Models of Natural Source Code

We study the problem of building generative models of natural source cod...

0 Chris J. Maddison, et al. ∙

Chris J. Maddison

Featured Co-authors