David Barber

is this you? claim profile

0 followers
UCL

Variational f-divergence Minimization

Probabilistic models are often trained by maximum likelihood, which corr...
07/27/2019 ∙ by Mingtian Zhang, et al. ∙ 9 ∙ share

read it
Gaussian mixture models with Wasserstein distance

Generative models with both discrete and continuous latent variables are...
06/12/2018 ∙ by Benoit Gaujac, et al. ∙ 4 ∙ share

read it
Private Machine Learning via Randomised Response

We introduce a general learning framework for private machine learning b...
01/14/2020 ∙ by David Barber, et al. ∙ 4 ∙ share

read it
Thinking Fast and Slow with Deep Learning and Tree Search

Sequential decision making problems, such as structured prediction, robo...
05/23/2017 ∙ by Thomas Anthony, et al. ∙ 0 ∙ share

read it
Practical Gauss-Newton Optimisation for Deep Learning

We present an efficient block-diagonal ap- proximation to the Gauss-Newt...
06/12/2017 ∙ by Aleksandar Botev, et al. ∙ 0 ∙ share

read it
Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent

We present a unifying framework for adapting the update direction in gra...
07/07/2016 ∙ by Aleksandar Botev, et al. ∙ 0 ∙ share

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

We consider training probabilistic classifiers in the case of a large nu...
06/22/2016 ∙ by David Barber, et al. ∙ 0 ∙ share

read it
Efficient Inference in Markov Control Problems

Markov control algorithms that perform smooth, non-greedy updates of the...
02/14/2012 ∙ by Thomas Furmston, et al. ∙ 0 ∙ share

read it
Variational Optimization

We discuss a general technique that can be used to form a differentiable...
12/18/2012 ∙ by Joe Staines, et al. ∙ 0 ∙ share

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

Long Short-Term Memory (LSTM) is a popular approach to boosting the abil...
11/05/2017 ∙ by Zhen He, et al. ∙ 0 ∙ share

read it
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting

We introduce the Kronecker factored online Laplace approximation for ove...
05/20/2018 ∙ by Hippolyt Ritter, et al. ∙ 0 ∙ share

read it
Improving latent variable descriptiveness with AutoGen

Powerful generative models, particularly in Natural Language Modelling, ...
06/12/2018 ∙ by Alex Mansbridge, et al. ∙ 0 ∙ share

read it
Generating Sentences Using a Dynamic Canvas

We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a...
06/13/2018 ∙ by Harshil Shah, et al. ∙ 0 ∙ share

read it
Generative Neural Machine Translation

We introduce Generative Neural Machine Translation (GNMT), a latent vari...
06/13/2018 ∙ by Harshil Shah, et al. ∙ 0 ∙ share

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

Online Multi-Object Tracking (MOT) from videos is a challenging computer...
09/10/2018 ∙ by Zhen He, et al. ∙ 0 ∙ share

read it
Stochastic Variational Optimization

Variational Optimization forms a differentiable upper bound on an object...
09/13/2018 ∙ by Thomas Bird, et al. ∙ 0 ∙ share

read it
Spread Divergences

For distributions p and q with different support, the divergence general...
11/21/2018 ∙ by David Barber, et al. ∙ 0 ∙ share

read it
Modular Networks: Learning to Decompose Neural Computation

Scaling model capacity has been vital in the success of deep learning. F...
11/13/2018 ∙ by Louis Kirsch, et al. ∙ 0 ∙ share

read it
Gaussian Mean Field Regularizes by Limiting Learned Information

Variational inference with a factorized Gaussian posterior estimate is a...
02/12/2019 ∙ by Julius Kunze, et al. ∙ 0 ∙ share

read it
Practical Lossless Compression with Latent Variables using Bits Back Coding

Deep latent variable models have seen recent success in many data domain...
01/15/2019 ∙ by James Townsend, et al. ∙ 0 ∙ share

read it
HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models

We make the following striking observation: fully convolutional VAE mode...
12/20/2019 ∙ by James Townsend, et al. ∙ 0 ∙ share

read it

David Barber

Featured Co-authors

Jian Li

Liang Xiao

Guy Lever

Ilya Feige

Bowen Zheng

Zhen He

Thomas Anthony

Julius Kunze

Aleksandar Botev

Louis Kirsch

Hangen He

Variational f-divergence Minimization

Gaussian mixture models with Wasserstein distance

Private Machine Learning via Randomised Response

Thinking Fast and Slow with Deep Learning and Tree Search

Practical Gauss-Newton Optimisation for Deep Learning

Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent

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

Efficient Inference in Markov Control Problems

Variational Optimization

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

Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting

Improving latent variable descriptiveness with AutoGen

Generating Sentences Using a Dynamic Canvas

Generative Neural Machine Translation

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

Stochastic Variational Optimization

Spread Divergences

Modular Networks: Learning to Decompose Neural Computation

Gaussian Mean Field Regularizes by Limiting Learned Information

Practical Lossless Compression with Latent Variables using Bits Back Coding

HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models