Principal components analysis (PCA) is the optimal linear auto-encoder of data, and it is often used to construct features. Enforcing sparsity on the principal components can promote better generalization, while improving the interpretability of the features. We study the problem of constructing optimal sparse linear a…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “sparse auto-encoders”
Given a convolutional dictionary underlying a set of observed signals, can a carefully designed auto-encoder recover the dictionary in the presence of noise? We introduce an auto-encoder architecture, termed constrained recurrent sparse auto-encoder (CRsAE), that answers this question in the affirmative. Given an input…
New auto-encoder handles varying noise levels without retraining.
problem Auto-encoders degrade in noisy conditions.
method Formalized auto-encoders as transform learning, derived new architecture.
result Models generalize well to different noise levels.
Auto-Encoders are unsupervised models that aim to learn patterns from observed data by minimizing a reconstruction cost. The useful representations learned are often found to be sparse and distributed. On the other hand, compressed sensing and sparse coding assume a data generating process, where the observed data is g…
Improved sample complexity for Gaussian process approximations.
problem Efficiently approximating Gaussian processes with sparse spectrum.
method Improved sample complexity analysis and auto-encoding algorithm.
result Gaussian process predictions and model evidence can be well-approximated with low sample complexity.
New model reconstructs flow from sparse data with uncertainty quantification.
problem Reconstructing nonlinear flow from limited observations.
method Semi-Conditional Variational Autoencoder (SCVAE) for probabilistic flow reconstruction.
result SCVAE improves reconstruction accuracy compared to Gappy Proper Orthogonal Decomposition (GPOD).
This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and interpretable structure of the data. Additionally, we want this decomposition to…
This paper studies an intelligent ultimate technique for health-monitoring and prognostic of common rotary machine components, particularly bearings. During a run-to-failure experiment, rich unsupervised features from vibration sensory data are extracted by a trained sparse auto-encoder. Then, the correlation of the ex…
Proposes flexible auto-encoders for varying data dimensions.
problem Fixed latent dimensions limit data flexibility.
method Stochastic bottleneck with weighted dropouts.
result Seamless variable dimensionality reduction with high performance.
This paper introduces structure learning for autoencoder recommenders to improve performance and generalization.
problem Efficient training and generalization in sparse collaborative filtering data.
method Learn groups of related items and use this information to determine the connectivity structure of an auto-encoding neural network.
result The proposed structure learning method results in a sparse network that converges to a local optimum with smaller spectral norm and generalization error.
Develops MgCSL for discovering causal structures in high-dimensional data.
problem Discovering causal relationships from high-dimensional data with complex interplay of variables.
method MgCSL uses sparse auto-encoders for coarse-graining and multi-layer perceptrons for detailed analysis, introducing simplified acyclicity constraints.
result MgCSL outperforms existing methods and finds explainable causal connections in fMRI datasets.
We proposed a novel graph convolutional neural network that could construct a coarse, sparse latent point cloud from a dense, raw point cloud. With a novel non-isotropic convolution operation defined on irregular geometries, the model then can reconstruct the original point cloud from this latent cloud with fine detail…
Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the longer it takes to learn. We introduce a class of neural networks, termed RandNet, f…
Non-negative tensor factorization models enable predictive analysis on count data. Among them, Bayesian Poisson-Gamma models can derive full posterior distributions of latent factors and are less sensitive to sparse count data. However, current inference methods for these Bayesian models adopt restricted update rules f…
In this note we present a generative model of natural images consisting of a deep hierarchy of layers of latent random variables, each of which follows a new type of distribution that we call rectified Gaussian. These rectified Gaussian units allow spike-and-slab type sparsity, while retaining the differentiability nec…
Paper proposes a method to learn structure from data similarities.
problem Learning hidden structures in data beyond low-rank and sparsity.
method Explicitly models data relation, retaining pairwise similarities.
result Framework significantly improves performance on clustering and semisupervised classification.
The paper identifies saddlepoints in unsupervised auto-encoding neural nets.
problem The risk landscape of unsupervised least squares in auto-encoding neural nets.
method Established an equivalence between unsupervised least squares and principal manifolds, discussed regularization strategies for auto-encoders.
result All non-trivial critical points in auto-encoding are saddlepoints, which are degenerate in overcomplete auto-encoding.
DGA and DVGA learn disentangled graph representations to improve graph analysis.
problem Holistic graph auto-encoders fail to capture latent factors effectively.
method Design disentangled graph convolutional network and component-wise flow, impose independence constraints.
result Improved disentangled graph representations enhance graph analysis tasks.
We present two instances, L-GAE and L-VGAE, of the variational graph auto-encoding family (VGAE) based on separating feature propagation operations from graph convolution layers typically found in graph learning methods to a single linear matrix computation made prior to input in standard auto-encoder architectures. Th…
Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of the unknown data generating density. This paper contributes to the mathematical understanding of this phenomenon and helps define better justified sampling algorithms for deep learning based on auto-encoder v…
What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized recons…
The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) model, consisting of a cascade of convolutional sparse layers, provides a new interpretation of Convolutional Neural Networks (CNNs). Under this framework, the computation of the forward pass in a CNN is equivalent to a pursuit algorithm aiming to e…
Fisher Auto-Encodersstat.ML
Fisher auto-encoders use Fisher divergence for more robust generative modeling.
problem Model uncertainty in generative models.
method Minimizing Fisher divergence between true and modeled joint distributions.
result Fisher auto-encoders can more accurately quantify model uncertainty.
FF layers in transformers are nearly as interpretable as sparse autoencoders.
problem Comparing interpretability of feature vectors in FF layers vs. sparse autoencoders.
method Revisited interpretability of FF layers as key-value memories using modern benchmarks.
result FF and SAE feature vectors are similarly interpretable, but FFs can be better in some aspects.
Wasserstein Auto-Encodersstat.ML
We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for building a generative model of the data distribution. WAE minimizes a penalized form of the Wasserstein distance between the model distribution and the target distribution, which leads to a different regularizer than the one used by the Variational Aut…
Auto-encoders are among the most popular neural network architecture for dimension reduction. They are composed of two parts: the encoder which maps the model distribution to a latent manifold and the decoder which maps the latent manifold to a reconstructed distribution. However, auto-encoders are known to provoke cha…
Paper tackles outlier detection in signals modeled by generative models with theoretical guarantees.
problem Recovering signals from linear measurements with sparse outliers.
method Proposes an iterative ADMM algorithm and gradient descent algorithm for outlier detection using and squared norm minimization.
result Establishes theoretical recovery guarantees for signal reconstruction under sparse outliers.
Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source se…
Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimationstat.ML
Paper proposes a novel auto-encoder for latent density estimation.
problem Challenges of learning generative probabilistic models due to curse of dimensionality.
method Joint dimensionality reduction and non-parametric density estimation framework using a novel estimator.
result Proposed model achieves promising results on various datasets.
Develops a new non-adversarial framework for better generative models.
problem Inaccurate approximation of target distribution in latent space.
method Tessellated Wasserstein Auto-Encoders (TWAE) using centroidal Voronoi tessellation (CVT) to tessellate latent space.
result Significantly enhances generative performance in terms of FID compared to existing models.
Learning Deep Representation Without Parameter Inference for Nonlinear Dimensionality Reductioncs.LG
Unsupervised deep learning is one of the most powerful representation learning techniques. Restricted Boltzman machine, sparse coding, regularized auto-encoders, and convolutional neural networks are pioneering building blocks of deep learning. In this paper, we propose a new building block -- distributed random models…
In this paper, we propose a novel structure for a cross-modal data association, which is inspired by the recent research on the associative learning structure of the brain. We formulate the cross-modal association in Bayesian inference framework realized by a deep neural network with multiple variational auto-encoders …
Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the ava…
Recommender systems (RS) help users navigate large sets of items in the search for "interesting" ones. One approach to RS is Collaborative Filtering (CF), which is based on the idea that similar users are interested in similar items. Most model-based approaches to CF seek to train a machine-learning/data-mining model b…
Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…
Adaptive graph auto-encoder improves general data clustering.
problem Extending graph convolution networks to general clustering tasks.
method Adaptive graph construction based on generative perspective, novel decoder design.
result Model performs well in weighted graph scenarios.
We provide theoretical and empirical evidence that using tighter evidence lower bounds (ELBOs) can be detrimental to the process of learning an inference network by reducing the signal-to-noise ratio of the gradient estimator. Our results call into question common implicit assumptions that tighter ELBOs are better vari…
This paper considers the problem of recovering signals from compressed measurements contaminated with sparse outliers, which has arisen in many applications. In this paper, we propose a generative model neural network approach for reconstructing the ground truth signals under sparse outliers. We propose an iterative al…
The (variational) graph auto-encoder and its variants have been popularly used for representation learning on graph-structured data. While the encoder is often a powerful graph convolutional network, the decoder reconstructs the graph structure by only considering two nodes at a time, thus ignoring possible interaction…
CAE models learn complex manifold structures in data.
problem Flat latent spaces in auto-encoders fail to capture manifold structures.
method Proposes Chart Auto-Encoders (CAE) with a multi-chart latent space.
result CAE provides better data representation with manifold properties.
We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model us…
We study the role of latent space dimensionality in Wasserstein auto-encoders (WAEs). Through experimentation on synthetic and real datasets, we argue that random encoders should be preferred over deterministic encoders. We highlight the potential of WAEs for representation learning with promising results on a benchmar…
Improved reliability of machine learning predictions using variational auto-encoders.
problem Individual unreliability of machine learning models.
method Modified variational auto-encoders to identify a low-dimensional space for reliable classification.
result Improved reliability of predictions and robust identification of adversarial samples.
Self-supervised VAEs improve data compression and generation.
problem Efficient data compression and generation.
method Introducing self-supervised Variational Auto-Encoders with deterministic and discrete variational posteriors.
result Self-supervised VAEs simplify the objective function and improve data reconstruction.
AutoDiff combines auto-encoder and diffusion model for realistic tabular data synthesis.
problem Generating realistic synthetic tabular data with heterogeneous features.
method Employing auto-encoder architecture to handle tabular data's complexity.
result Synthetic tables from AutoDiff show good statistical fidelity and perform well in machine learning tasks.
AER combines auto-encoder and LSTM for better time series anomaly detection.
problem Anomaly detection in time series data with limited labeled data and ambiguous definitions.
method AER (Auto-Encoder with Regression) integrates auto-encoder and LSTM for joint predictions and reconstructions.
result AER achieves the highest F1 score across 12 datasets with comparable runtime.
Unbiased gradient estimation improves VAE performance.
problem Training VAEs via maximum likelihood is difficult due to intractable integrals.
method Introduced unbiased estimators of the log-likelihood gradient using coupled Markov chains.
result Unbiased estimators lead to better predictive performance in VAEs.
A Graph Feature Auto-Encoder for the Prediction of Unobserved Node Features on Biological Networksq-bio.QM
Graph auto-encoder predicts unobserved node features from biological networks and omics data.
problem Integrating biological networks and continuous node features for better prediction.
method Graph neural networks and feature auto-encoders trained on feature reconstruction.
result Graph feature auto-encoder outperforms auto-encoders trained on graph reconstruction for predicting unobserved node features.