Frank Wood

is this you? claim profile

∙ 0 followers
University of Oxford ∙ The University of British Columbia

Associate Professor at University of Oxford, Faculty Fellow at The Alan Turing Institute, Consultant at Invrea Limited

Imagining The Road Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation

We develop a deep generative model built on a fully differentiable simul...
04/22/2021 ∙ by Adam Ścibior, et al. ∙ 9 ∙ share

read it
Image Completion via Inference in Deep Generative Models

We consider image completion from the perspective of amortized inference...
02/24/2021 ∙ by William Harvey, et al. ∙ 8 ∙ share

read it
Robust Asymmetric Learning in POMDPs

Policies for partially observed Markov decision processes can be efficie...
12/31/2020 ∙ by Andrew Warrington, et al. ∙ 0 ∙ share

read it
Annealed Importance Sampling with q-Paths

Annealed importance sampling (AIS) is the gold standard for estimating p...
12/14/2020 ∙ by Rob Brekelmans, et al. ∙ 8 ∙ share

read it
Ensemble Squared: A Meta AutoML System

The continuing rise in the number of problems amenable to machine learni...
12/10/2020 ∙ by Jason Yoo, et al. ∙ 0 ∙ share

read it
Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

Achieving the full promise of the Thermodynamic Variational Objective (T...
10/29/2020 ∙ by Vu Nguyen, et al. ∙ 11 ∙ share

read it
Uncertainty in Neural Processes

We explore the effects of architecture and training objective choice on ...
10/08/2020 ∙ by Saeid Naderiparizi, et al. ∙ 7 ∙ share

read it
Assisting the Adversary to Improve GAN Training

We propose a method for improved training of generative adversarial netw...
10/03/2020 ∙ by Andreas Munk, et al. ∙ 2 ∙ share

read it
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference

The recently proposed Thermodynamic Variational Objective (TVO) leverage...
07/01/2020 ∙ by Rob Brekelmans, et al. ∙ 9 ∙ share

read it
Semi-supervised Sequential Generative Models

We introduce a novel objective for training deep generative time-series ...
06/30/2020 ∙ by Michael Teng, et al. ∙ 10 ∙ share

read it
Improving Few-Shot Visual Classification with Unlabelled Examples

We propose a transductive meta-learning method that uses unlabelled inst...
06/17/2020 ∙ by Peyman Bateni, et al. ∙ 0 ∙ share

read it
Planning as Inference in Epidemiological Models

In this work we demonstrate how existing software tools can be used to a...
03/30/2020 ∙ by Frank Wood, et al. ∙ 34 ∙ share

read it
Coping With Simulators That Don't Always Return

Deterministic models are approximations of reality that are easy to inte...
03/28/2020 ∙ by Andrew Warrington, et al. ∙ 6 ∙ share

read it
Improved Few-Shot Visual Classification

Few-shot learning is a fundamental task in computer vision that carries ...
12/07/2019 ∙ by Peyman Bateni, et al. ∙ 1 ∙ share

read it
Attention for Inference Compilation

We present a new approach to automatic amortized inference in universal ...
10/25/2019 ∙ by William Harvey, et al. ∙ 21 ∙ share

read it
Deep Probabilistic Surrogate Networks for Universal Simulator Approximation

We present a framework for automatically structuring and training fast, ...
10/25/2019 ∙ by Andreas Munk, et al. ∙ 40 ∙ share

read it
Amortized Rejection Sampling in Universal Probabilistic Programming

Existing approaches to amortized inference in probabilistic programs wit...
10/20/2019 ∙ by Saeid Naderiparizi, et al. ∙ 11 ∙ share

read it
Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation

Imitation learning is a promising approach to end-to-end training of aut...
09/20/2019 ∙ by Renhao Wang, et al. ∙ 0 ∙ share

read it
The Virtual Patch Clamp: Imputing C. elegans Membrane Potentials from Calcium Imaging

We develop a stochastic whole-brain and body simulator of the nematode r...
07/24/2019 ∙ by Andrew Warrington, et al. ∙ 5 ∙ share

read it
Amortized Monte Carlo Integration

Current approaches to amortizing Bayesian inference focus solely on appr...
07/18/2019 ∙ by Adam Golinski, et al. ∙ 2 ∙ share

read it
Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale

Probabilistic programming languages (PPLs) are receiving widespread atte...
07/08/2019 ∙ by Atılım Güneş Baydin, et al. ∙ 2 ∙ share

read it
The Thermodynamic Variational Objective

We introduce the thermodynamic variational objective (TVO) for learning ...
06/28/2019 ∙ by Vaden Masrani, et al. ∙ 2 ∙ share

read it
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training

We introduce the use of Bayesian optimal experimental design techniques ...
06/13/2019 ∙ by William Harvey, et al. ∙ 0 ∙ share

read it
Imitation Learning of Factored Multi-agent Reactive Models

We apply recent advances in deep generative modeling to the task of imit...
03/12/2019 ∙ by Michael Teng, et al. ∙ 11 ∙ share

read it
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models

We develop a new Low-level, First-order Probabilistic Programming Langua...
03/06/2019 ∙ by Yuan Zhou, et al. ∙ 12 ∙ share

read it
An Introduction to Probabilistic Programming

This document is designed to be a first-year graduate-level introduction...
09/27/2018 ∙ by Jan-Willem van de Meent, et al. ∙ 2 ∙ share

read it
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

We present a novel framework that enables efficient probabilistic infere...
07/20/2018 ∙ by Atilim Gunes Baydin, et al. ∙ 4 ∙ share

read it
Inference Trees: Adaptive Inference with Exploration

We introduce inference trees (ITs), a new class of inference methods tha...
06/25/2018 ∙ by Tom Rainforth, et al. ∙ 2 ∙ share

read it
Deep Variational Reinforcement Learning for POMDPs

Many real-world sequential decision making problems are partially observ...
06/06/2018 ∙ by Maximilian Igl, et al. ∙ 2 ∙ share

read it
Revisiting Reweighted Wake-Sleep

Discrete latent-variable models, while applicable in a variety of settin...
05/26/2018 ∙ by Tuan Anh Le, et al. ∙ 0 ∙ share

read it
Discontinuous Hamiltonian Monte Carlo for Probabilistic Programs

Hamiltonian Monte Carlo (HMC) is the dominant statistical inference algo...
04/07/2018 ∙ by Bradley Gram-Hansen, et al. ∙ 0 ∙ share

read it
High Throughput Synchronous Distributed Stochastic Gradient Descent

We introduce a new, high-throughput, synchronous, distributed, data-para...
03/12/2018 ∙ by Michael Teng, et al. ∙ 0 ∙ share

read it
Tighter Variational Bounds are Not Necessarily Better

We provide theoretical and empirical evidence that using tighter evidenc...
02/13/2018 ∙ by Tom Rainforth, et al. ∙ 0 ∙ share

read it
Improvements to Inference Compilation for Probabilistic Programming in Large-Scale Scientific Simulators

We consider the problem of Bayesian inference in the family of probabili...
12/21/2017 ∙ by Mario Lezcano Casado, et al. ∙ 0 ∙ share

read it
Faithful Model Inversion Substantially Improves Auto-encoding Variational Inference

In learning deep generative models, the encoder for variational inferenc...
12/01/2017 ∙ by Stefan Webb, et al. ∙ 0 ∙ share

read it
Updating the VESICLE-CNN Synapse Detector

We present an updated version of the VESICLE-CNN algorithm presented by ...
10/31/2017 ∙ by Andrew Warrington, et al. ∙ 0 ∙ share

read it
On the Opportunities and Pitfalls of Nesting Monte Carlo Estimators

We present a formalization of nested Monte Carlo (NMC) estimation, where...
09/18/2017 ∙ by Tom Rainforth, et al. ∙ 0 ∙ share

read it
Bayesian Optimization for Probabilistic Programs

We present the first general purpose framework for marginal maximum a po...
07/13/2017 ∙ by Tom Rainforth, et al. ∙ 0 ∙ share

read it
Learning Disentangled Representations with Semi-Supervised Deep Generative Models

Variational autoencoders (VAEs) learn representations of data by jointly...
06/01/2017 ∙ by N. Siddharth, et al. ∙ 0 ∙ share

read it
Auto-Encoding Sequential Monte Carlo

We introduce AESMC: a method for using deep neural networks for simultan...
05/29/2017 ∙ by Tuan Anh Le, et al. ∙ 0 ∙ share

read it
Online Learning Rate Adaptation with Hypergradient Descent

We introduce a general method for improving the convergence rate of grad...
03/14/2017 ∙ by Atilim Gunes Baydin, et al. ∙ 0 ∙ share

read it
Using Synthetic Data to Train Neural Networks is Model-Based Reasoning

We draw a formal connection between using synthetic training data to opt...
03/02/2017 ∙ by Tuan Anh Le, et al. ∙ 0 ∙ share

read it
Inducing Interpretable Representations with Variational Autoencoders

We develop a framework for incorporating structured graphical models in ...
11/22/2016 ∙ by N. Siddharth, et al. ∙ 0 ∙ share

read it
Probabilistic structure discovery in time series data

Existing methods for structure discovery in time series data construct i...
11/21/2016 ∙ by David Janz, et al. ∙ 0 ∙ share

read it
Inference Compilation and Universal Probabilistic Programming

We introduce a method for using deep neural networks to amortize the cos...
10/31/2016 ∙ by Tuan Anh Le, et al. ∙ 0 ∙ share

read it
Spreadsheet Probabilistic Programming

Spreadsheet workbook contents are simple programs. Because of this, prob...
06/14/2016 ∙ by Mike Wu, et al. ∙ 0 ∙ share

read it
Inference Networks for Sequential Monte Carlo in Graphical Models

We introduce a new approach for amortizing inference in directed graphic...
02/22/2016 ∙ by Brooks Paige, et al. ∙ 0 ∙ share

read it
Interacting Particle Markov Chain Monte Carlo

We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a P...
02/16/2016 ∙ by Tom Rainforth, et al. ∙ 0 ∙ share

read it
Semantics for probabilistic programming: higher-order functions, continuous distributions, and soft constraints

We study the semantic foundation of expressive probabilistic programming...
01/19/2016 ∙ by Sam Staton, et al. ∙ 0 ∙ share

read it
Data-driven Sequential Monte Carlo in Probabilistic Programming

Most of Markov Chain Monte Carlo (MCMC) and sequential Monte Carlo (SMC)...
12/14/2015 ∙ by Yura N Perov, et al. ∙ 0 ∙ share

read it

Frank Wood

Featured Co-authors