
-
Locally-Contextual Nonlinear CRFs for Sequence Labeling
Linear chain conditional random fields (CRFs) combined with contextual w...
read it
-
Reducing the Computational Cost of Deep Generative Models with Binary Neural Networks
Deep generative models provide a powerful set of tools to understand rea...
read it
-
Learning to Noise: Application-Agnostic Data Sharing with Local Differential Privacy
In recent years, the collection and sharing of individuals' private data...
read it
-
Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
Probabilistic models with hierarchical-latent-variable structures provid...
read it
-
Learning disentangled representations with the Wasserstein Autoencoder
Disentangled representation learning has undoubtedly benefited from obje...
read it
-
Bayesian Online Meta-Learning with Laplace Approximation
Neural networks are known to suffer from catastrophic forgetting when tr...
read it
-
Private Machine Learning via Randomised Response
We introduce a general learning framework for private machine learning b...
read it
-
HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models
We make the following striking observation: fully convolutional VAE mode...
read it
-
Variational f-divergence Minimization
Probabilistic models are often trained by maximum likelihood, which corr...
read it
-
Gaussian Mean Field Regularizes by Limiting Learned Information
Variational inference with a factorized Gaussian posterior estimate is a...
read it
-
Practical Lossless Compression with Latent Variables using Bits Back Coding
Deep latent variable models have seen recent success in many data domain...
read it
-
Spread Divergences
For distributions p and q with different support, the divergence general...
read it
-
Modular Networks: Learning to Decompose Neural Computation
Scaling model capacity has been vital in the success of deep learning. F...
read it
-
Stochastic Variational Optimization
Variational Optimization forms a differentiable upper bound on an object...
read it
-
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
Online Multi-Object Tracking (MOT) from videos is a challenging computer...
read it
-
Generative Neural Machine Translation
We introduce Generative Neural Machine Translation (GNMT), a latent vari...
read it
-
Generating Sentences Using a Dynamic Canvas
We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a...
read it
-
Improving latent variable descriptiveness with AutoGen
Powerful generative models, particularly in Natural Language Modelling, ...
read it
-
Gaussian mixture models with Wasserstein distance
Generative models with both discrete and continuous latent variables are...
read it
-
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
We introduce the Kronecker factored online Laplace approximation for ove...
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...
read it
-
Practical Gauss-Newton Optimisation for Deep Learning
We present an efficient block-diagonal ap- proximation to the Gauss-Newt...
read it
-
Thinking Fast and Slow with Deep Learning and Tree Search
Sequential decision making problems, such as structured prediction, robo...
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...
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...
read it
-
Variational Optimization
We discuss a general technique that can be used to form a differentiable...
read it
-
Efficient Inference in Markov Control Problems
Markov control algorithms that perform smooth, non-greedy updates of the...
read it