b'Frank Wood'

research

∙ 06/17/2022

Conditional Permutation Invariant Flows

We present a novel, conditional generative probabilistic model of set-va...

Berend Zwartsenberg, et al. ∙

research

∙ 05/30/2022

Critic Sequential Monte Carlo

We introduce CriticSMC, a new algorithm for planning as inference built ...

Vasileios Lioutas, et al. ∙

research

∙ 05/23/2022

Flexible Diffusion Modeling of Long Videos

We present a framework for video modeling based on denoising diffusion p...

William Harvey, et al. ∙

research

∙ 05/20/2022

BayesPCN: A Continually Learnable Predictive Coding Associative Memory

Associative memory plays an important role in human intelligence and its...

Jason Yoo, et al. ∙

research

∙ 02/17/2022

Gradients without Backpropagation

Using backpropagation to compute gradients of objective functions for op...

Atılım Güneş Baydin, et al. ∙

research

∙ 02/06/2022

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Distributional reinforcement learning (RL) aims to learn a value-network...

Michael Teng, et al. ∙

research

∙ 01/13/2022

Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning

Modern deep learning requires large-scale extensively labelled datasets ...

Peyman Bateni, et al. ∙

research

∙ 07/01/2021

q-Paths: Generalizing the Geometric Annealing Path using Power Means

Many common machine learning methods involve the geometric annealing pat...

Vaden Masrani, et al. ∙

research

∙ 06/18/2021

Differentiable Particle Filtering without Modifying the Forward Pass

In recent years particle filters have being used as components in system...

Adam Ścibior, et al. ∙

research

∙ 04/22/2021

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

We develop a deep generative model built on a fully differentiable simul...

Adam Ścibior, et al. ∙

research

∙ 02/24/2021

Image Completion via Inference in Deep Generative Models

We consider image completion from the perspective of amortized inference...

William Harvey, et al. ∙

research

∙ 12/31/2020

Robust Asymmetric Learning in POMDPs

Policies for partially observed Markov decision processes can be efficie...

Andrew Warrington, et al. ∙

research

∙ 12/14/2020

Annealed Importance Sampling with q-Paths

Annealed importance sampling (AIS) is the gold standard for estimating p...

Rob Brekelmans, et al. ∙

research

∙ 12/10/2020

Ensemble Squared: A Meta AutoML System

The continuing rise in the number of problems amenable to machine learni...

Jason Yoo, et al. ∙

research

∙ 10/29/2020

Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective

Achieving the full promise of the Thermodynamic Variational Objective (T...

Vu Nguyen, et al. ∙

research

∙ 10/08/2020

Uncertainty in Neural Processes

We explore the effects of architecture and training objective choice on ...

Saeid Naderiparizi, et al. ∙

research

∙ 10/03/2020

Assisting the Adversary to Improve GAN Training

We propose a method for improved training of generative adversarial netw...

Andreas Munk, et al. ∙

research

∙ 07/01/2020

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

The recently proposed Thermodynamic Variational Objective (TVO) leverage...

Rob Brekelmans, et al. ∙

research

∙ 06/30/2020

Semi-supervised Sequential Generative Models

We introduce a novel objective for training deep generative time-series ...

Michael Teng, et al. ∙

research

∙ 06/17/2020

Improving Few-Shot Visual Classification with Unlabelled Examples

We propose a transductive meta-learning method that uses unlabelled inst...

Peyman Bateni, et al. ∙

research

∙ 03/30/2020

Planning as Inference in Epidemiological Models

In this work we demonstrate how existing software tools can be used to a...

Frank Wood, et al. ∙

research

∙ 03/28/2020

Coping With Simulators That Don't Always Return

Deterministic models are approximations of reality that are easy to inte...

Andrew Warrington, et al. ∙

research

∙ 12/07/2019

Improved Few-Shot Visual Classification

Few-shot learning is a fundamental task in computer vision that carries ...

Peyman Bateni, et al. ∙

research

∙ 10/25/2019

Attention for Inference Compilation

We present a new approach to automatic amortized inference in universal ...

William Harvey, et al. ∙

research

∙ 10/25/2019

Deep Probabilistic Surrogate Networks for Universal Simulator Approximation

We present a framework for automatically structuring and training fast, ...

Andreas Munk, et al. ∙

research

∙ 10/20/2019

Amortized Rejection Sampling in Universal Probabilistic Programming

Existing approaches to amortized inference in probabilistic programs wit...

Saeid Naderiparizi, et al. ∙

research

∙ 09/20/2019

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...

Renhao Wang, et al. ∙

research

∙ 07/24/2019

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...

Andrew Warrington, et al. ∙

research

∙ 07/18/2019

Amortized Monte Carlo Integration

Current approaches to amortizing Bayesian inference focus solely on appr...

Adam Golinski, et al. ∙

research

∙ 07/08/2019

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale

Probabilistic programming languages (PPLs) are receiving widespread atte...

Atılım Güneş Baydin, et al. ∙

research

∙ 06/28/2019

The Thermodynamic Variational Objective

We introduce the thermodynamic variational objective (TVO) for learning ...

Vaden Masrani, et al. ∙

research

∙ 06/13/2019

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

We introduce the use of Bayesian optimal experimental design techniques ...

William Harvey, et al. ∙

research

∙ 03/12/2019

Imitation Learning of Factored Multi-agent Reactive Models

We apply recent advances in deep generative modeling to the task of imit...

Michael Teng, et al. ∙

research

∙ 03/06/2019

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...

Yuan Zhou, et al. ∙

research

∙ 09/27/2018

An Introduction to Probabilistic Programming

This document is designed to be a first-year graduate-level introduction...

Jan-Willem van de Meent, et al. ∙

research

∙ 07/20/2018

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

We present a novel framework that enables efficient probabilistic infere...

Atilim Gunes Baydin, et al. ∙

research

∙ 06/25/2018

Inference Trees: Adaptive Inference with Exploration

We introduce inference trees (ITs), a new class of inference methods tha...

Tom Rainforth, et al. ∙

research

∙ 06/06/2018

Deep Variational Reinforcement Learning for POMDPs

Many real-world sequential decision making problems are partially observ...

Maximilian Igl, et al. ∙

research

∙ 05/26/2018

Revisiting Reweighted Wake-Sleep

Discrete latent-variable models, while applicable in a variety of settin...

Tuan Anh Le, et al. ∙

research

∙ 04/07/2018

Discontinuous Hamiltonian Monte Carlo for Probabilistic Programs

Hamiltonian Monte Carlo (HMC) is the dominant statistical inference algo...

Bradley Gram-Hansen, et al. ∙

research

∙ 03/12/2018

High Throughput Synchronous Distributed Stochastic Gradient Descent

We introduce a new, high-throughput, synchronous, distributed, data-para...

Michael Teng, et al. ∙

research

∙ 02/13/2018

Tighter Variational Bounds are Not Necessarily Better

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

Tom Rainforth, et al. ∙

research

∙ 12/21/2017

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

We consider the problem of Bayesian inference in the family of probabili...

Mario Lezcano Casado, et al. ∙

research

∙ 12/01/2017

Faithful Model Inversion Substantially Improves Auto-encoding Variational Inference

In learning deep generative models, the encoder for variational inferenc...

Stefan Webb, et al. ∙

research

∙ 10/31/2017

Updating the VESICLE-CNN Synapse Detector

We present an updated version of the VESICLE-CNN algorithm presented by ...

Andrew Warrington, et al. ∙

research

∙ 09/18/2017

On the Opportunities and Pitfalls of Nesting Monte Carlo Estimators

We present a formalization of nested Monte Carlo (NMC) estimation, where...

Tom Rainforth, et al. ∙

research

∙ 07/13/2017

Bayesian Optimization for Probabilistic Programs

We present the first general purpose framework for marginal maximum a po...

Tom Rainforth, et al. ∙

research

∙ 06/01/2017

Learning Disentangled Representations with Semi-Supervised Deep Generative Models

Variational autoencoders (VAEs) learn representations of data by jointly...

N. Siddharth, et al. ∙

research

∙ 05/29/2017

Auto-Encoding Sequential Monte Carlo

We introduce AESMC: a method for using deep neural networks for simultan...

Tuan Anh Le, et al. ∙

research

∙ 03/14/2017

Online Learning Rate Adaptation with Hypergradient Descent

We introduce a general method for improving the convergence rate of grad...

Atilim Gunes Baydin, et al. ∙

Frank Wood

Featured Co-authors