Open AccessPosted Content
DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
TLDR
The authors proposed a new class of smoothing transformations based on a mixture of two overlapping distributions, and showed that the proposed transformation can be used for training binary latent models with either directed or undirected priors.Abstract:
Training of discrete latent variable models remains challenging because passing gradient information through discrete units is difficult We propose a new class of smoothing transformations based on a mixture of two overlapping distributions, and show that the proposed transformation can be used for training binary latent models with either directed or undirected priors We derive a new variational bound to efficiently train with Boltzmann machine priors Using this bound, we develop DVAE++, a generative model with a global discrete prior and a hierarchy of convolutional continuous variables Experiments on several benchmarks show that overlapping transformations outperform other recent continuous relaxations of discrete latent variables including Gumbel-Softmax (Maddison et al, 2016; Jang et al, 2016), and discrete variational autoencoders (Rolfe 2016)read more
Citations
More filters
Journal ArticleDOI
Handling incomplete heterogeneous data using VAEs
Alfredo Nazábal,Pablo M. Olmos,Zoubin Ghahramani,Zoubin Ghahramani,Isabel Valera,Isabel Valera +5 more
TL;DR: A general framework to design VAEs suitable for fitting incomplete heterogenous data, which includes likelihood models for real-valued, positive real valued, interval, categorical, ordinal and count data, and allows accurate estimation of missing data is proposed.
Posted Content
PixelVAE++: Improved PixelVAE with Discrete Prior
TL;DR: PixelVAE++ as mentioned in this paper combines the best features of the two models and constructs a generative model that is able to learn local and global structures, achieving state-of-the-art performance on binary data sets.
Posted Content
Direct Optimization through $\arg \max$ for Discrete Variational Auto-Encoder
TL;DR: In this article, direct loss minimization is applied to variational autoencoders with both unstructured and structured discrete latent variables to reduce the variance of their gradient estimates.
Posted Content
Estimation of Dimensions Contributing to Detected Anomalies with Variational Autoencoders.
TL;DR: This paper proposes a novel algorithm for estimating the dimensions contributing to the detected anomalies by using variational autoencoders (VAEs), based on an approximative probabilistic model that considers the existence of anomalies in the data, and by maximizing the log-likelihood estimates which dimensions contribute to determining data as an anomaly.
Posted Content
GumBolt: Extending Gumbel trick to Boltzmann priors
TL;DR: GumBolt as mentioned in this paper extends the Gumbel trick to BM priors in VAEs and achieves state-of-the-art performance on permutation invariant MNIST and OMNIGLOT datasets.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Posted Content
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: In this article, the adaptive estimates of lower-order moments are used for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimate of lowerorder moments.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.