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.
Paired autoencoders solve inverse problems using latent space projections.
A new method for conditional sampling using paired Wasserstein Autoencoders.
Gene expression profiles have been widely used to characterize patterns of cellular responses to diseases. As data becomes available, scalable learning toolkits become essential to processing large datasets using deep learning models to model complex biological processes. We present an autoencoder to capture nonlinear …
Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing cross-view learning algorithms assume access to paired data for training. Their applicabi…
Bayesian autoencoders improve OOD detection by addressing Bernoulli likelihood issues.
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…
Modeling spillover effects from observational data is an important problem in economics, business, and other fields of research. % It helps us infer the causality between two seemingly unrelated set of events. For example, if consumer spending in the United States declines, it has spillover effects on economies that de…
Bidirectional VAE reduces parameters and improves image tasks.
The autoencoder is an artificial neural network model that learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar…
This paper introduces a cross adversarial source separation (CASS) framework via autoencoder, a new model that aims at separating an input signal consisting of a mixture of multiple components into individual components defined via adversarial learning and autoencoder fitting. CASS unifies popular generative networks l…
New function-space autoencoders improve data handling across resolutions.
Drug-drug interactions (DDIs) are a major cause of preventable hospitalizations and deaths. Predicting the occurrence of DDIs helps drug safety professionals allocate investigative resources and take appropriate regulatory action promptly. Traditional DDI prediction methods predict DDIs based on the similarity between …
We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform u…
Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods. In particular, graph AE and VAE were successfully leveraged to tackle the challenging link prediction problem, aiming at figuring out whether some pairs of nodes from a graph are connected by unobserved edges…
Improved clustering accuracy with disentangled latent code representation.
OGAN attacks autoencoders to prevent deepfake creation.
The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distributi…
Simpler autoencoder with regularization outperforms complex alternatives.
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoe…
Weak supervision enables learning causal representations from unstructured data.
The paper proposes a method to learn differentially private variational autoencoders with term-wise gradient aggregation.
The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned by stochastic gradient variational Bayes. We first elaborate Gaussian VAE, approximating the local covariance matrix of the decoder as an o…
GROOVE learns representations for weakly paired multimodal data.
Proposes ACLAE-DT for unsupervised anomaly detection in multivariate time series.
Method reconstructs aneurysm growth history from patient parameters using physics-informed autoencoder.
Deep generative models have achieved remarkable success in various data domains, including images, time series, and natural languages. There remain, however, substantial challenges for combinatorial structures, including graphs. One of the key challenges lies in the difficulty of ensuring semantic validity in context. …
Paper tackles missing data in irregularly-sampled time series.
New autoencoder framework learns structured latent priors.
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental…
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
Autoencoders compress and reconstruct data for various applications.
Proposes a Bayesian Autoencoder with sparse Gaussian process priors to capture data correlations.
Study on dynamics of non-linear autoencoders learning principal components.
NestedVAE isolates common factors from paired images without additional supervision.
Proposes CCCVAE for better single-cell clustering with cell-cell communication.
Chart autoencoders learn latent features preserving manifold topology and geometry, with robust denoising capabilities.
Improved code translation by preserving structure with composed fine-tuning.
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be successfully recovered. Motivated by a real-world problem, we propose a setting where …
POTATOES improves autoencoder UOD accuracy without tuning.
SuTaT creates dialogue summaries for tete-a-tetes without labeled data.
In this paper we propose a Deep Autoencoder MIxture Clustering (DAMIC) algorithm based on a mixture of deep autoencoders where each cluster is represented by an autoencoder. A clustering network transforms the data into another space and then selects one of the clusters. Next, the autoencoder associated with this clust…
A novel ML verification technique using manifold learning.
A new model learns graph structures from data.
AEGCN uses autoencoder constraints to improve graph node classification.
GE-autoencoder identifies spontaneous symmetry breaking in systems.
Regularization preserves topological data structure in autoencoders.
A new autoencoder method uses empirical beta copulas for generating data.
Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.