arXiv research

New method learns disentangled discrete representations using categorical variational autoencoders.

New JSA autoencoders tackle discrete latent variable models for semi-supervised learning.

New estimators reduce variance in training variational autoencoders with discrete latent variables.

Probabilistic models with discrete latent variables naturally capture datasets composed of discrete classes. However, they are difficult to train efficiently, since backpropagation through discrete variables is generally not possible. We present a novel method to train a class of probabilistic models with discrete late…

VADD enhances discrete diffusion models by capturing inter-dimensional correlations, improving sample quality.

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 lat…

DVAEs speed up calorimeter simulation for LHC data.

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters throug…

New approach handles stochastic and partially-observable environments using discrete autoencoders and Monte Carlo tree search.

A new method scales Gaussian process variational autoencoders to handle high-dimensional time series.

Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used the evidence lower bound and not the tighter importance-weighted bound. We propose two approaches fo…

Improves gradient estimation for discrete distributions with variance reduction techniques.

Proposes a VAE with a discrete bottleneck for better text generation.

Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data. Although probabilistic matrix factorisation and linear/nonlinear latent factor models have enjoyed great success in modell…

A new model trains prior and encoder/decoder networks simultaneously for efficient generation.

A new method learns discrete representations for images and videos, improving upon previous models.

A new method reduces variance in training discrete latent variable models.

DD-VAE uses deterministic decoding for better latent code utilization in discrete data.

We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent…

Improved hierarchical discrete VAEs for better stability and performance.

Improved vector quantization using Gaussian mixtures for better codebook utilization.

Novel SVAE learns interpretable discrete data representations from deep learning.

Deep neural networks with discrete latent variables offer the promise of better symbolic reasoning, and learning abstractions that are more useful to new tasks. There has been a surge in interest in discrete latent variable models, however, despite several recent improvements, the training of discrete latent variable m…

A new model tackles language generation issues by using discrete variational attention.

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often …

This paper introduces lattice representations for efficient discrete learning.

The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.

TES-AE uses tree grammars to speed up autoencoding for tree data.

In this work, we propose a new recurrent autoencoder architecture, termed Feedback Recurrent AutoEncoder (FRAE), for online compression of sequential data with temporal dependency. The recurrent structure of FRAE is designed to efficiently extract the redundancy along the time dimension and allows a compact discrete re…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content from the signal, e.g.\ phoneme identities, while being invariant to confounding l…

LaMBO optimizes biological sequences using autoencoders and Bayesian optimization.

Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets. They present, however, subtleties in training often manifesting in the discrete latent being under leveraged. In this paper, we show that such models are more amenable to training whe…

Direct optimization of binary latent VAEs achieves competitive results without sampling.

We introduce the concrete autoencoder, an end-to-end differentiable method for global feature selection, which efficiently identifies a subset of the most informative features and simultaneously learns a neural network to reconstruct the input data from the selected features. Our method is unsupervised, and is based on…

Diffusion models generate music sequences without autoregressive loops.

Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max trick, but the resulting objective relies on an $\arg \max$ operation and is non-dif…

NegBio-VAE models neural spike counts with negative binomial distribution.

Variational autoencoders (VAEs) are powerful generative models with the salient ability to perform inference. Here, we introduce a quantum variational autoencoder (QVAE): a VAE whose latent generative process is implemented as a quantum Boltzmann machine (QBM). We show that our model can be trained end-to-end by maximi…

A new gradient estimator reduces variance near boundaries for binary latent variables.

Method generates counterfactual explanations for graph classifiers.

A new method uncovers discrete and continuous factors in gene expression data.

VANO uses neural operators for unsupervised learning of functional data.

The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a distribution. Here, we propose an extension of the VAE framework that incorporates a classi…

In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior are trained jointly to minimize a rate-distortion loss, which is closely relate…

Deep generative models are attracting great attention as a new promising approach for molecular design. All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN). Here we propose a new type model based on an adversarially regularized autoencoder (ARAE). It basi…

VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-V…

We introduce the thermodynamic variational objective (TVO) for learning in both continuous and discrete deep generative models. The TVO arises from a key connection between variational inference and thermodynamic integration that results in a tighter lower bound to the log marginal likelihood than the standard variatio…

A new Multi-Stream VAE separates multiple sources in images and audio.