
Bias Mitigated Learning from Differentially Private Synthetic Data: A Cautionary Tale
Increasing interest in privacypreserving machine learning has led to ne...
read it

Quantitative Uniform Stability of the Iterative Proportional Fitting Procedure
We establish the uniform in time stability, w.r.t. the marginals, of the...
read it

Monte Carlo Variational AutoEncoders
Variational autoencoders (VAE) are popular deep latent variable models ...
read it

Wide stochastic networks: Gaussian limit and PACBayesian training
The limit of infinite width allows for substantial simplifications in th...
read it

Diffusion Schrödinger Bridge with Applications to ScoreBased Generative Modeling
Progressively applying Gaussian noise transforms complex data distributi...
read it

On Instrumental Variable Regression for Deep Offline Policy Evaluation
We show that the popular reinforcement learning (RL) strategy of estimat...
read it

Invertible Flow Non Equilibrium sampling
Simultaneously sampling from a complex distribution with intractable nor...
read it

COIN: COmpression with Implicit Neural representations
We propose a new simple approach for image compression: instead of stori...
read it

Improving Lossless Compression Rates via Monte Carlo BitsBack Coding
Latent variable models have been successfully applied in lossless compre...
read it

Differentiable Particle Filtering via EntropyRegularized Optimal Transport
Particle Filtering (PF) methods are an established class of procedures f...
read it

Annealed Flow Transport Monte Carlo
Annealed Importance Sampling (AIS) and its Sequential Monte Carlo (SMC) ...
read it

Generative Models as Distributions of Functions
Generative models are typically trained on gridlike data such as images...
read it

MetropolisHastings with Averaged Acceptance Ratios
Markov chain Monte Carlo (MCMC) methods to sample from a probability dis...
read it

Stable ResNet
Deep ResNet architectures have achieved state of the art performance on ...
read it

Learning Deep Features in Instrumental Variable Regression
Instrumental variable (IV) regression is a standard strategy for learnin...
read it

Unbiased Gradient Estimation for Variational AutoEncoders using Coupled Markov Chains
The variational autoencoder (VAE) is a deep latent variable model that ...
read it

A Particle Method for Solving Fredholm Equations of the First Kind
Fredholm integral equations of the first kind are the prototypical examp...
read it

Variational Inference with ContinuouslyIndexed Normalizing Flows
Continuouslyindexed flows (CIFs) have recently achieved improvements ov...
read it

Pruning untrained neural networks: Principles and Analysis
Overparameterized neural networks display stateofthe art performance. ...
read it

Ensemble Rejection Sampling
We introduce Ensemble Rejection Sampling, a scheme for exact simulation ...
read it

Schrödinger Bridge Samplers
Consider a reference Markov process with initial distribution π_0 and tr...
read it

Nonreversible jump algorithms for Bayesian nested model selection
Nonreversible Markov chain Monte Carlo methods often outperform their r...
read it

Localised Generative Flows
We argue that flowbased density models based on continuous bijections a...
read it

Modular MetaLearning with Shrinkage
Most gradientbased approaches to metalearning do not explicitly accoun...
read it

Training Dynamics of Deep Networks using Stochastic Gradient Descent via Neural Tangent Kernel
Stochastic Gradient Descent (SGD) is widely used to train deep neural ne...
read it

Efficient MCMC Sampling with DimensionFree Convergence Rate using ADMMtype Splitting
Performing exact Bayesian inference for complex models is intractable. M...
read it

Replica Conditional Sequential Monte Carlo
We propose a Markov chain Monte Carlo (MCMC) scheme to perform state inf...
read it

NonReversible Parallel Tempering: an Embarassingly Parallel MCMC Scheme
Parallel tempering (PT) methods are a popular class of Markov chain Mont...
read it

Augmented Neural ODEs
We show that Neural Ordinary Differential Equations (ODEs) learn represe...
read it

Bernoulli Race Particle Filters
When the weights in a particle filter are not available analytically, st...
read it

On the Impact of the Activation Function on Deep Neural Networks Training
The weight initialization and the activation function of deep neural net...
read it

Unbiased Smoothing using Particle Independent MetropolisHastings
We consider the approximation of expectations with respect to the distri...
read it

Scalable MetropolisHastings for Exact Bayesian Inference with Large Datasets
Bayesian inference via standard Markov Chain Monte Carlo (MCMC) methods ...
read it

Hamiltonian Descent Methods
We propose a family of optimization methods that achieve linear converge...
read it

Scalable Monte Carlo inference for statespace models
We present an original simulationbased method to estimate likelihood ra...
read it

Randomized Hamiltonian Monte Carlo as Scaling Limit of the Bouncy Particle Sampler and DimensionFree Convergence Rates
The Bouncy Particle Sampler is a Markov chain Monte Carlo method based o...
read it

Unbiased Markov chain Monte Carlo for intractable target distributions
Performing numerical integration when the integrand itself cannot be eva...
read it

Limit theorems for sequential MCMC methods
Sequential Monte Carlo (SMC) methods, also known as particle filters, co...
read it

Large Sample Asymptotics of the PseudoMarginal Method
The pseudomarginal algorithm is a variant of the MetropolisHastings al...
read it

Stability of Optimal Filter HigherOrder Derivatives
In many scenarios, a statespace model depends on a parameter which need...
read it

Bias of Particle Approximations to Optimal Filter Derivative
In many applications, a statespace model depends on a parameter which n...
read it

Analyticity of Entropy Rates of ContinuousState Hidden Markov Models
The analyticity of the entropy and relative entropy rates of continuous...
read it

Asymptotic Properties of Recursive Maximum Likelihood Estimation in NonLinear StateSpace Models
Using stochastic gradient search and the optimal filter derivative, it i...
read it

Hamiltonian Variational AutoEncoder
Variational AutoEncoders (VAEs) have become very popular techniques to ...
read it

On the Selection of Initialization and Activation Function for Deep Neural Networks
The weight initialization and the activation function of deep neural net...
read it

On the utility of MetropolisHastings with asymmetric acceptance ratio
The MetropolisHastings algorithm allows one to sample asymptotically fr...
read it

Asymptotic Bias of Stochastic Gradient Search
The asymptotic behavior of the stochastic gradient algorithm with a bias...
read it

Controlled Sequential Monte Carlo
Sequential Monte Carlo (SMC) methods are a set of simulationbased techn...
read it

Filtering Variational Objectives
When used as a surrogate objective for maximum likelihood estimation in ...
read it

PseudoMarginal Hamiltonian Monte Carlo
Bayesian inference in the presence of an intractable likelihood function...
read it
Arnaud Doucet
verfied profile
Professor of Statistics at Oxford University & Research Scientist at Google DeepMind