D. Barber

发表

Ensemble learning in Bayesian neural networks

Charles M. Bishop, D. Barber, 1998 .

Thinking Fast and Slow with Deep Learning and Tree Search

David Barber, Thomas Anthony, Zheng Tian, 2017, NIPS.

FINITE-SIZE EFFECTS AND OPTIMAL TEST SET SIZE IN LINEAR PERCEPTRONS

D. Saad, D. Barber, Peter Sollich, 1995 .

The IM algorithm: a variational approach to Information Maximization

David Barber, Felix V. Agakov, F. Agakov, 2003, NIPS 2003.

Variational methods for Reinforcement Learning

David Barber, Thomas Furmston, D. Barber, 2010, AISTATS.

Solving deterministic policy ( PO ) MDPs using Expectation-Maximisation and Antifreeze

D. Barber, T. Furmston, 2009 .

Bayesian Time Series Models: Inference and estimation in probabilistic time series models

D. Barber, S. Chiappa, A. Cemgil, 2011 .

Kernelized Infomax Clustering

David Barber, Felix V. Agakov, F. Agakov, 2005, NIPS.

Bayesian reasoning and machine learning

David Barber, D. Barber, 2012 .

The Auxiliary Variable Trick for deriving Kalman Smoothers

D. Barber, 2004 .

Bayesian Linear Gaussian State Space Models for Biosignal Decomposition

D. Barber, S. Chiappa, 2005 .

Switch-Reset Models : Exact and Approximate Inference

D. Barber, Chris Bracegirdle, 2011, AISTATS.

Are two Classifiers performing equally? A treatment using Bayesian Hypothesis Testing

D. Barber, 2004 .

Gaussian Processes for Bayesian Classification via Hybrid Monte Carlo

David Barber, Christopher K. I. Williams, D. Barber, 1996, NIPS.

Modular Networks: Learning to Decompose Neural Computation

David Barber, Julius Kunze, Louis Kirsch, 2018, NeurIPS.

Concave Gaussian Variational Approximations for Inference in Large-Scale Bayesian Linear Models

David Barber, Edward Challis, D. Barber, 2011, AISTATS.

Online Learning from Finite Training Sets and Robustness to Input Bias

David Barber, Peter Sollich, D. Barber, 1998, Neural Computation.

Online Learning from Nite Training Sets

D. Barber, 1997 .

Variational f-divergence Minimization pdf

David Barber, Tianlin Xu, Mingtian Zhang, 2019, ArXiv.

Bayesian Classification With Gaussian Processes

David Barber, Christopher K. I. Williams, D. Barber, 1998, IEEE Trans. Pattern Anal. Mach. Intell..

Gaussian Mean Field Regularizes by Limiting Learned Information

David Barber, Julius Kunze, Louis Kirsch, 2019, Entropy.

Affine Independent Variational Inference

David Barber, Edward Challis, D. Barber, 2012, NIPS.

Ensemble Learning for Multi-Layer Networks

David Barber, Christopher M. Bishop, Charles M. Bishop, 1997, NIPS.

Variational Belief Networks for Approximate InferenceWim Wiegerinck

W. Wiegerinck, D. Barber, 1998 .

Mean Field Theory based on Belief Networks for Approximate Inference

W. Wiegerinck, D. Barber, 1998 .

Approximate Newton Methods for Policy Search in Markov Decision Processes

David Barber, Guy Lever, Thomas Furmston, 2016, J. Mach. Learn. Res..

Expectation Correction for Smoothed Inference in Switching Linear Dynamical Systems

David Barber, D. Barber, 2006, J. Mach. Learn. Res..

Nesterov's accelerated gradient and momentum as approximations to regularised update descent

David Barber, Guy Lever, Aleksandar Botev, 2016, 2017 International Joint Conference on Neural Networks (IJCNN).

An Auxiliary Variational Method

David Barber, Felix V. Agakov, F. Agakov, 2004, ICONIP.

Temporal Hidden Hopfield Models

F. Agakov, D. Barber, 2002 .

Tractable Variational Structures for Approximating Graphical Models

David Barber, Wim Wiegerinck, W. Wiegerinck, 1998, NIPS.

Variational Cumulant Expansions for Intractable Distributions

David Barber, Piërre van de Laar, D. Barber, 2011, J. Artif. Intell. Res..

Variational Cumulant Expansions for Intractable Distributions Pi Erre Van De Laar

D. Barber, 1999 .

Variational Information Maximization for Population Coding

D. Barber, 2004 .

Variational Information Maximization in Gaussian Channels

F. Agakov, D. Barber, 2004 .

Latent Variable Models

D. Barber, Julius Kunze, 2019, Bayesian Econometric Methods.

Variational Optimization pdf

David Barber, Joe Staines, D. Barber, 2012, ArXiv.

Identifying graph clusters using variational inference and links to covariance parametrization

David Barber, D. Barber, 2009, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

Construction and comparison of approximations for switching linear gaussian state space models

David Barber, D. Barber, 2005 .

Inference and learning in latent Markov models

D. Barber, S. Chiappa, 2015 .

05-06 Construction and comparison of approximations for switching linear gaussian state space models

D. Barber, B. Mesot, 2005 .

Research Report 05-06 Construction and comparison of approximations for switching linear gaussian state space models

D. Barber, B. Mesot, 2022 .

Learning as inference

David Barber, D. Barber, 2011 .

Deterministic approximate inference

David Barber, D. Barber, 2011 .

Improving Gaussian mixture latent variable model convergence with Optimal Transport

David Barber, Ilya Feige, Benoit Gaujac, 2018, ACML.

Auxiliary Variational MCMC

David Barber, Raza Habib, D. Barber, 2018, International Conference on Learning Representations.

Bayesian Time Series Models: Plate section

David Barber, Silvia Chiappa, A. Taylan Cemgil, 2011 .

Adaptive Optimization with Examplewise Gradients pdf

David Barber, Julius Kunze, James Townsend, 2021, ArXiv.

Locally-Contextual Nonlinear CRFs for Sequence Labeling pdf

David Barber, Harshil Shah, Tim Z. Xiao, 2021, ArXiv.

Probabilistic knowledge representation

David Barber, Hilbert J. Kappen, Wim Wiegerinck, 1998 .

Efficient inference in trees

David Barber, D. Barber, 2012 .

Bayesian Time Series Models: Preface

David Barber, Silvia Chiappa, A. Taylan Cemgil, 2011 .

Stochastic POMDP controllers: How easy to optimize?

David Barber, Michael L. Littman, Nikos Vlassis, 2012 .

Efficiently labelling sequences using semi-supervised active learning

David Barber, Harshil Shah, D. Barber, 2020 .

S.A. Solla, T.K. Leen and K-R. M. Miller, editors, Advances in Neural Information Processing Systems

David Barber, Peter Sollich, D. Barber, 2000 .

On Computing the KL Divergence for Bayesian Neural Networks

David Barber, Christopher M. Bishop, C. Bishop, 1997 .

Application of Generative Temporal Independent Component Analysis for EEG Classification in Asynchronous BCI Systems

D. Barber, S. Chiappa, 2022 .

A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes

D. Barber, T. Furmston, 2012, NIPS.

Stable Directed Belief Propagation in Gaussian DAGs using the auxiliary variable trick

David Barber, Peter Sollich, D. Barber, 2005 .

Gene regulatory network inference using sparse probabilistic models

D. Barber, 2011 .

Spread Divergence

D. Barber, Mingtian Zhang, Thomas Bird, 2018, ICML.

On the Computational Complexity of Stochastic Controller Optimization in POMDPs

David Barber, Michael L. Littman, Nikos Vlassis, 2011, TOCT.

Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting

David Barber, Hippolyt Ritter, Aleksandar Botev, 2018, NeurIPS.

Practical Gauss-Newton Optimisation for Deep Learning

David Barber, Hippolyt Ritter, Aleksandar Botev, 2017, ICML.

Switching Linear Dynamical Systems for Noise Robust Speech Recognition

David Barber, Bertrand Mesot, D. Barber, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Complementary Sum Sampling for Likelihood Approximation in Large Scale Classification

David Barber, Bowen Zheng, Aleksandar Botev, 2017, AISTATS.

Gaussian Kullback-Leibler approximate inference

David Barber, Edward Challis, D. Barber, 2013, J. Mach. Learn. Res..

Graphical Models for Time-Series

David Barber, Ali Taylan Cemgil, D. Barber, 2010, IEEE Signal Processing Magazine.

Learning disentangled representations with the Wasserstein Autoencoder

David Barber, Ilya Feige, Benoit Gaujac, 2020, ECML/PKDD.

Dealing with a large number of classes -- Likelihood, Discrimination or Ranking?

David Barber, Aleksandar Botev, D. Barber, 2016, 1606.06959.

Dynamic Bayesian Networks with Deterministic Latent Tables

David Barber, D. Barber, 2002, NIPS.

Efficient Inference in Markov Control Problems

David Barber, Thomas Furmston, D. Barber, 2011, UAI.

A Scalable Laplace Approximation for Neural Networks

David Barber, Hippolyt Ritter, Aleksandar Botev, 2018, ICLR.

Generalization Gap in Amortized Inference

D. Barber, Mingtian Zhang, Peter Hayes, 2022, NeurIPS.

HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models pdf

David Barber, Julius Kunze, James Townsend, 2019, ICLR.

Practical Lossless Compression with Latent Variables using Bits Back Coding pdf

David Barber, James Townsend, Tom Bird, 2019, ICLR.

Spread Divergences pdf

David Barber, Mingtian Zhang, Raza Habib, 2019, ArXiv.

The Auxiliary Variable Trick for deriving

D. Barber, 2005 .

Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning

Liang Xiao, David Barber, Daxue Liu, 2017, NIPS.

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

David Barber, Jian Li, Daxue Liu, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Towards Algorithm Auditing: A Survey on Managing Legal, Ethical and Technological Risks of AI, ML and Associated Algorithms

Adriano Soares Koshiyama, D. Barber, P. Treleaven, 2021 .

Optimization by Variational Bounding

David Barber, Joe Staines, D. Barber, 2013, ESANN.

Variational methods for approximate reasoning in graphical models

David Barber, Tom Heskes, Hilbert J. Kappen, 2000 .

Variational Cumulant Expansions for Intractable Distributions Pi Erre Van De Laar

D. Barber, 1999 .

Unified Inference for Variational Bayesian Linear Gaussian State-Space Models

David Barber, Silvia Chiappa, D. Barber, 2006, NIPS.

Finite size effects in neural network algorithms

David Barber, D. Barber, 1996 .

Approximate Learning in Temporal Hidden Hopfield Models

David Barber, Felix V. Agakov, F. Agakov, 2003, ICANN.

Tractable Undirected Approximations for Graphical Models

David Barber, Wim Wiegerinck, W. Wiegerinck, 1998 .

Gaussian mixture models with Wasserstein distance pdf

David Barber, Ilya Feige, Benoit Gaujac, 2018, ArXiv.

Bayesian Online Meta-Learning with Laplace Approximation pdf

David Barber, Hippolyt Ritter, Pau Ching Yap, 2020, ArXiv.

Generating Sentences Using a Dynamic Canvas

David Barber, Bowen Zheng, Harshil Shah, 2018, AAAI.

Generative Neural Machine Translation

David Barber, Harshil Shah, D. Barber, 2018, NeurIPS.

Gaussian Processes for Bayesian Estimation in Ordinary Differential Equations

David Barber, Yali Wang, D. Barber, 2014, ICML.

A Simple Alternative Derivation of the Expectation Correction Algorithm

David Barber, Bertrand Mesot, D. Barber, 2009, IEEE Signal Processing Letters.

A Novel Gaussian Sum Smoother for Approximate Inference in Switching Linear Dynamical Systems

David Barber, Bertrand Mesot, D. Barber, 2006, NIPS.

Gaussian Fields for Approximate Inference in Layered Sigmoid Belief Networks

David Barber, Peter Sollich, D. Barber, 1999, NIPS.

Information Maximization in Noisy Channels : A Variational Approach

David Barber, Felix Agakov, F. Agakov, 2003, NIPS.

EEG classification using generative independent component analysis

David Barber, Silvia Chiappa, D. Barber, 2006, Neurocomputing.

A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes

David Barber, Thomas Furmston, D. Barber, 2012, NIPS.

Bayesian Time Series Models

David Barber, Silvia Chiappa, A. Taylan Cemgil, 2011 .

Learning in Spiking Neural Assemblies

David Barber, D. Barber, 2002, NIPS.

Lagrange Dual Decomposition for Finite Horizon Markov Decision Processes

David Barber, Thomas Furmston, D. Barber, 2011, ECML/PKDD.

Dynamical Dirichlet Mixture Model

David Barber, Jean-Marc Odobez, Le Chen, 2007 .

Bayesian Time Series Models

Christopher K. I. Williams, John Quinn, D. Barber, 2011 .

Stochastic Variational Optimization pdf

David Barber, Julius Kunze, Thomas Bird, 2018, ArXiv.

Bayesian Model Comparison by Monte Carlo Chaining

David Barber, Christopher M. Bishop, Charles M. Bishop, 1996, NIPS.

Bayesian Online Meta-Learning

D. Barber, H. Ritter, Pauching Yap, 2020 .