David Barber
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
David Barber has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Mingtian Zhang
University College London University College London Imperial College London University College London
2 shared publications - Chris Bracegirdle
Centre for Computational Statistics and Machine Learning University College London Gower Street London
1 shared publication - James Townsend
AI Center University College London
1 shared publication - Michael L. Littman
Brown University, Providence, Rhode Island, USA
1 shared publication - Nikos Vlassis
University of Luxembourg
1 shared publication - Ning Kang
Huawei Noah's Ark Lab
1 shared publication
Latest Publications
- Open Access
Generalization Gap in Amortized Inference
The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression. In this work, we study the generalization of a popular class of probabilistic model - the Variational Auto-Encoder (VAE). We discuss the two generalization gaps that affect VAEs and show that overfitting is usually dominated by amortized inference. Based on this observation, we propose a new training objective that improves the generalization of amortized inference. We demonstrate how our method can improve performance in the context of image modeling and lossless compression.
Open AccessGeneralization Gap in Amortized Inference
The ability of likelihood-based probabilistic models to generalize to unseen data is central to many machine learning applications such as lossless compression. In this work, we study the generalization of a popular class of probabilistic model - the Variational Auto-Encoder (VAE). We discuss the two generalization gaps that affect VAEs and show that overfitting is usually dominated by amortized inference. Based on this observation, we propose a new training objective that improves the generalization of amortized inference. We demonstrate how our method can improve performance in the context of image modeling and lossless compression.
- Open Access
Parallel Neural Local Lossless Compression
The recently proposed Neural Local Lossless Compression (NeLLoC), which is based on a local autoregressive model, has achieved state-of-the-art (SOTA) out-of-distribution (OOD) generalization performance in the image compression task. In addition to the encouragement of OOD generalization, the local model also allows parallel inference in the decoding stage. In this paper, we propose two parallelization schemes for local autoregressive models. We discuss the practicalities of implementing the schemes and provide experimental evidence of significant gains in compression runtime compared to the previous, non-parallel implementation.
Open AccessParallel Neural Local Lossless Compression
The recently proposed Neural Local Lossless Compression (NeLLoC), which is based on a local autoregressive model, has achieved state-of-the-art (SOTA) out-of-distribution (OOD) generalization performance in the image compression task. In addition to the encouragement of OOD generalization, the local model also allows parallel inference in the decoding stage. In this paper, we propose two parallelization schemes for local autoregressive models. We discuss the practicalities of implementing the schemes and provide experimental evidence of significant gains in compression runtime compared to the previous, non-parallel implementation.
- Open Access
On the Computational Complexity of Stochastic Controller Optimization in POMDPs
We show that the problem of finding an optimal stochastic 'blind' controller in a Markov decision process is an NP-hard problem. The corresponding decision problem is NP-hard, in PSPACE, and SQRT-SUM-hard, hence placing it in NP would imply breakthroughs in long-standing open problems in computer science. Our result establishes that the more general problem of stochastic controller optimization in POMDPs is also NP-hard. Nonetheless, we outline a special case that is convex and admits efficient global solutions.
Open AccessOn the Computational Complexity of Stochastic Controller Optimization in POMDPs
We show that the problem of finding an optimal stochastic 'blind' controller in a Markov decision process is an NP-hard problem. The corresponding decision problem is NP-hard, in PSPACE, and SQRT-SUM-hard, hence placing it in NP would imply breakthroughs in long-standing open problems in computer science. Our result establishes that the more general problem of stochastic controller optimization in POMDPs is also NP-hard. Nonetheless, we outline a special case that is convex and admits efficient global solutions.
- Open Access
Bayesian Conditional Cointegration
Cointegration is an important topic for time-series, and describes a relationship between two series in which a linear combination is stationary. Classically, the test for cointegration is based on a two stage process in which first the linear relation between the series is estimated by Ordinary Least Squares. Subsequently a unit root test is performed on the residuals. A well-known deficiency of this classical approach is that it can lead to erroneous conclusions about the presence of cointegration. As an alternative, we present a framework for estimating whether cointegration exists using Bayesian inference which is empirically superior to the classical approach. Finally, we apply our technique to model segmented cointegration in which cointegration may exist only for limited time. In contrast to previous approaches our model makes no restriction on the number of possible cointegration segments.
Open AccessBayesian Conditional Cointegration
Cointegration is an important topic for time-series, and describes a relationship between two series in which a linear combination is stationary. Classically, the test for cointegration is based on a two stage process in which first the linear relation between the series is estimated by Ordinary Least Squares. Subsequently a unit root test is performed on the residuals. A well-known deficiency of this classical approach is that it can lead to erroneous conclusions about the presence of cointegration. As an alternative, we present a framework for estimating whether cointegration exists using Bayesian inference which is empirically superior to the classical approach. Finally, we apply our technique to model segmented cointegration in which cointegration may exist only for limited time. In contrast to previous approaches our model makes no restriction on the number of possible cointegration segments.
- 13 November 2009
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 367 (1906) , 4407-4426
Identifying graph clusters using variational inference and links to covariance parametrization
Finding clusters of well-connected nodes in a graph is a problem common to many domains, including social networks, the Internet and bioinformatics. From a computational viewpoint, finding these clusters or graph communities is a difficult problem. We use a clique matrix decomposition based on a statistical description that encourages clusters to be well connected and few in number. The formal intractability of inferring the clusters is addressed using a variational approximation inspired by mean-field theories in statistical mechanics. Clique matrices also play a natural role in parametrizing positive definite matrices under zero constraints on elements of the matrix. We show that clique matrices can parametrize all positive definite matrices restricted according to a decomposable graph and form a structured factor analysis approximation in the non-decomposable case. Extensions to conjugate Bayesian covariance priors and more general non-Gaussian independence models are briefly discussed.
- 13 November 2009
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 367 (1906) , 4407-4426
Identifying graph clusters using variational inference and links to covariance parametrization
Finding clusters of well-connected nodes in a graph is a problem common to many domains, including social networks, the Internet and bioinformatics. From a computational viewpoint, finding these clusters or graph communities is a difficult problem. We use a clique matrix decomposition based on a statistical description that encourages clusters to be well connected and few in number. The formal intractability of inferring the clusters is addressed using a variational approximation inspired by mean-field theories in statistical mechanics. Clique matrices also play a natural role in parametrizing positive definite matrices under zero constraints on elements of the matrix. We show that clique matrices can parametrize all positive definite matrices restricted according to a decomposable graph and form a structured factor analysis approximation in the non-decomposable case. Extensions to conjugate Bayesian covariance priors and more general non-Gaussian independence models are briefly discussed.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 18455921,p. 446-451
Output Grouping using Dirichlet Mixtures of Linear Gaussian State-Space Models
We consider a model to cluster the components of a vector time-series. The task is to assign each component of the vector time-series to a single cluster, basing this assignment on the simultaneous dynamical similarity of the component to other components in the cluster. This is in contrast to the more familiar task of clustering a set of time-series based on global measures of their similarity. The model is based on a Dirichlet Mixture of Linear Gaussian State-Space models (LGSSMs), in which each LGSSM is treated with a prior to encourage the simplest explanation. The resulting model is approximated using a 'collapsed' variational Bayes implementation.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 18455921,p. 446-451
Output Grouping using Dirichlet Mixtures of Linear Gaussian State-Space Models
We consider a model to cluster the components of a vector time-series. The task is to assign each component of the vector time-series to a single cluster, basing this assignment on the simultaneous dynamical similarity of the component to other components in the cluster. This is in contrast to the more familiar task of clustering a set of time-series based on global measures of their similarity. The model is based on a Dirichlet Mixture of Linear Gaussian State-Space models (LGSSMs), in which each LGSSM is treated with a prior to encourage the simplest explanation. The resulting model is approximated using a 'collapsed' variational Bayes implementation.