A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
SurVAE Flows combine VAEs and flows using surjective transformations.
This paper clarifies VAE's property through geometric and information-theoretic interpretations.
UT module refines VAE latent space, improving disentanglement and interpretability.
Variational autoencoder is a powerful deep generative model with variational inference. The practice of modeling latent variables in the VAE's original formulation as normal distributions with a diagonal covariance matrix limits the flexibility to match the true posterior distribution. We propose a new transformation, …
Automates galaxy morphology classification with less human labelling.
Generative Adversarial Nets (GANs) and Variational Auto-Encoders (VAEs) provide impressive image generations from Gaussian white noise, but the underlying mathematics are not well understood. We compute deep convolutional network generators by inverting a fixed embedding operator. Therefore, they do not require to be o…
Proposes an ensemble framework combining VAE, Transformer, and LSTM for stock price prediction.
VAEs and GANs use simple distributions and neural networks to implicitly approximate complex data distributions.
Identifying customer segments in retail banking portfolios with different risk profiles can improve the accuracy of credit scoring. The Variational Autoencoder (VAE) has shown promising results in different research domains, and it has been documented the powerful information embedded in the latent space of the VAE. We…
Exemplar VAEs link generative models with nearest neighbor retrieval and data augmentation.
Self-supervised VAEs improve data compression and generation.
A new method generates synthetic data with realistic marginal distributions.
Long-term human motion can be represented as a series of motion modes---motion sequences that capture short-term temporal dynamics---with transitions between them. We leverage this structure and present a novel Motion Transformation Variational Auto-Encoders (MT-VAE) for learning motion sequence generation. Our model j…
Proposes a supervised VAE to reveal model invariances for interpretability.
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…
We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single abstraction---the random variable. Our lightweight implementation in TensorFlow enables numerous applications: a model-parallel variational …
T2IVAE detects anomalies in time series data with high accuracy.
VAELLS learns latent manifold structure to improve VAE model accuracy.
Wavelets improve VAE image quality.
A new loss function for VAEs improves image quality and efficiency.
Jukebox generates high-fidelity songs with singing in raw audio.
ES-VAE models skeletal pose trajectories by removing nuisance factors.
Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the approximations to the posterior flexible and accurate, leading to tremendous progress. Howe…
Variational auto-encoders (VAE) are scalable and powerful generative models. However, the choice of the variational posterior determines tractability and flexibility of the VAE. Commonly, latent variables are modeled using the normal distribution with a diagonal covariance matrix. This results in computational efficien…
A new text representation model combines CNN and VAE for better semantic extraction.
Generative model improves tabular data density estimation.
An ability to model a generative process and learn a latent representation for speech in an unsupervised fashion will be crucial to process vast quantities of unlabelled speech data. Recently, deep probabilistic generative models such as Variational Autoencoders (VAEs) have achieved tremendous success in modeling natur…
SAHMM-VAE separates sources adaptively using hidden Markov priors.
CausalVAE learns causal relationships in VAE models for better data disentanglement.
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…
Parallelizes autoregressive generation using VSSM.
With the advent of deep generative models in computational chemistry, in silico anticancer drug design has undergone an unprecedented transformation. While state-of-the-art deep learning approaches have shown potential in generating compounds with desired chemical properties, they disregard the genetic profile and prop…
Constructing VAE Latent Spaces with Prescribed Topology
This paper addresses problematic global optima in VAEs, proposing a new inference method.
Anomaly detection is a classical but worthwhile problem, and many deep learning-based anomaly detection algorithms have been proposed, which can usually achieve better detection results than traditional methods. In view of reconstruct ability of the model and the calculation of anomaly score, this paper proposes a time…
Improved IFA with Generative Adversarial Networks for high-dimensional latent variables.
In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance und…
Neural samplers such as variational autoencoders (VAEs) or generative adversarial networks (GANs) approximate distributions by transforming samples from a simple random source---the latent space---to samples from a more complex distribution represented by a dataset. While the manifold hypothesis implies that the densit…
Unified approach to DP problems using Gumbel distribution and variational Bayesian inference.
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling approach to compress temporal sequences with a focus on video. Our approach builds upon…
This work tackles posterior collapse in conditional and hierarchical VAEs.
InfoMax-VAE enhances VAEs for better representation learning.
trVAE improves conditional out-of-sample generation for unpaired data.
BS-VAE separates decoder variance and beta to improve VAE performance.
A tutorial on VAEs explaining its derivation and applications.
New system for i-vector speaker recognition based on variational autoencoder (VAE) is investigated. VAE is a promising approach for developing accurate deep nonlinear generative models of complex data. Experiments show that VAE provides speaker embedding and can be effectively trained in an unsupervised manner. LLR est…
Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on learning are largely unexplored. Further, the Gaussian prior assumptions in model…
The paper provides convergence guarantees for VAEs using SGD and Adam.