Variational autoencoders learn deep latent models.
problem Learning deep latent-variable models.
method Principled framework using variational inference.
result Introduction to variational autoencoders and extensions.
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “correspondence autoencoder”
New autoencoder framework learns structured latent priors.
problem Learning autoencoders with flexible priors.
method Relational regularization on latent prior, scalable algorithms.
result RAE outperforms existing autoencoders in image generation.
We provide a series of results for unsupervised learning with autoencoders. Specifically, we study shallow two-layer autoencoder architectures with shared weights. We focus on three generative models for data that are common in statistical machine learning: (i) the mixture-of-gaussians model, (ii) the sparse coding mod…
A new method explains Siamese neural networks using feature comparison and autoencoder.
problem Explaining the decision-making process of Siamese neural networks.
method Feature comparison at embedding level and autoencoder reconstruction.
result The method effectively explains Siamese neural networks using MNIST dataset.
New framework for multi-domain translation using autoencoders.
problem Learning probabilistic coupling between different domains.
method Learning multiple uncoupled autoencoders under shared latent distribution.
result New autoencoders can be added sequentially without retraining.
Sigmoid autoencoders can implement associative memory with certain conditions.
problem Implementing associative memory in neural networks.
method Theoretical analysis of overparameterized sigmoid autoencoders using the NTK and iterative maps.
result Overparameterized sigmoid autoencoders can have attractors in the NTK limit, leading to associative memory.
AEGCN uses autoencoder constraints to improve graph node classification.
problem Node classification on graph domains with reduced information loss.
method Autoencoder-constrained graph convolutional network (AEGCN).
result Adding autoencoder constraints significantly improves graph convolutional network performance.
A Novel Fusion of Attention and Sequence to Sequence Autoencoders to Predict Sleepiness From Speecheess.AS
Novel fusion of autoencoders predicts sleepiness from speech.
problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.
We explore the question of whether the representations learned by classifiers can be used to enhance the quality of generative models. Our conjecture is that labels correspond to characteristics of natural data which are most salient to humans: identity in faces, objects in images, and utterances in speech. We propose …
AMBER method selects features efficiently using autoencoders and model-based elimination.
problem Efficiently selecting relevant features for classification.
method Greedy backward elimination using a ranker model and autoencoders.
result AMBER outperforms other feature selection methods in classification accuracy.
Graphon autoencoder generates graphs with arbitrary sizes using Chebyshev filters.
problem Generating graphs with arbitrary sizes and arbitrary structures.
method Induces graphons from observed graphs, uses Chebyshev filters for latent representation, and learns encoder and decoder to minimize Wasserstein distance.
result Graphon autoencoder provides a new paradigm for graph generation with good generalizability and transferability.
Improved unsupervised word translation using adversarial autoencoder with cycle consistency and input reconstruction.
problem Challenging language pairs and lack of parallel data for unsupervised word translation.
method Adversarial autoencoder with cycle consistency and input reconstruction regularization.
result More stable and better performance than recent approaches.
Conformal Autoencoders infer intrinsic dimensionality and impose invariance.
problem Detecting intrinsic dimensionality and imposing invariance in nonlinear manifold data.
method Imposing orthogonality conditions on latent variables to infer intrinsic dimensionality and build coordinate invariance.
result The method can infer intrinsic dimensionality and build coordinate invariance on submanifolds.
Proposes a VAE with Student- mixture model for authorship attribution.
problem Traditional authorship attribution in closed-set scenarios.
method Extends variational autoencoder with embedded Student- mixture model.
result Superior performance over existing methods on Amazon review dataset.
Improved ASR-free keyword spotting in under-resourced languages.
problem Dynamic time warping for keyword spotting in languages with limited resources.
method Multilingual bottleneck extractor and correspondence autoencoder integration.
result More than 11% absolute improvement in ROC AUC over MFCCs.
Deep Automodulatorscs.LG
Automodulators generate and blend images from multiple sources.
problem Generating and blending images from multiple sources.
method Decouples decoder operations from latent vectors, using a principled approach for mutual disentanglement.
result Sharp outputs in high resolution, nearly indistinguishable from GANs.
The Autoencoder Reconstruction Ratio detects increased asset co-movements.
problem Detecting changes in asset co-movements for risk management.
method Uses a deep sparse denoising autoencoder to measure asset returns with latent variables.
result Lower ARR values indicate periods of market weakness and increased volatility.
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…
EVGAE improves VGAE's latent representation learning by mitigating over-pruning.
problem Over-pruning in VGAE limits latent variable capacity and diversity.
method EVGAE uses epitomic approach with multiple sparse VGAE models (epitomes) to increase active latent units and improve generative ability.
result EVGAE outperforms VGAE in generative ability and link prediction on citation networks.
Improving Bi-directional Generation between Different Modalities with Variational Autoencodersstat.ML
We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to achieve this objective is to train a model that integrates all the information of different modalities into a joint representation and then t…
Proposes NC-VAE to prevent posterior collapse in VAEs.
problem Posterior collapse in variational autoencoders (VAEs).
method Noise contrastive estimation applied to VAEs.
result Proves NC-VAE cannot reach posterior collapse and provides lower bounds.
Improved emotion prediction using autoencoder codebooks.
problem Continuous emotion prediction from audio data.
method Bag-of-Words model based on autoencoder codebook.
result Improved CCC scores for emotion dimensions.
Proposes SDCN to integrate structural information into deep clustering.
problem Lack of attention to structural information in representation learning for clustering.
method Designs a delivery operator to transfer autoencoder representations to GCN layers and uses a dual self-supervised mechanism.
result SDCN consistently outperforms state-of-the-art techniques in clustering tasks.
This work analyzes autoencoders to understand feature learning, revealing different phases of learning.
problem Understanding the feature extraction mechanism in weight-tied autoencoders.
method Mean field analysis of two-layer weight-tied autoencoders trained with stochastic gradient descent.
result The training dynamics of autoencoders exhibit different phases corresponding to learning different principal subspaces of the data.
New approach corrects latent space degeneracy in Variational Autoencoders.
problem Degeneracy in latent space of Variational Autoencoders.
method Perturbation theory to correct degeneracy in latent space.
result Corrected latent space degeneracy, leading to interpretable embeddings.
Improves VAE training by refining variational parameters with BSVI.
problem Amortized inference in VAEs leads to suboptimal variational parameters and the amortization gap.
method Proposes BSVI, a refinement procedure using SVI's importance weights.
result Training VAEs with BSVI yields improved performance compared to SVI.
Linear VAEs explain posterior collapse in VAEs via local maxima in log marginal likelihood.
problem Posterior collapse in VAEs where variational posterior matches prior for some latent variables.
method Analysis of linear VAEs and their relation to pPCA, proving ELBO does not introduce spurious local maxima.
result Linear VAEs have identifiable global maxima corresponding to principal component directions, explaining posterior collapse.
A CAE improves DNN's outlier and adversary defense.
problem Improving DNN's robustness against outliers and adversaries.
method Proposes a classification-autoencoder (CAE) that compresses samples into disjoint spaces and uses a decoder to classify and defend against adversaries.
result The CAE achieves state-of-the-art outlier recognition and near-lossless classification of adversaries.
New insights into Deep Autoencoders for better data approximation and generalization.
problem Understanding and improving generalization of deep learning models with more parameters than data.
method Interpreting Deep Autoencoders' structure and using Lie group theory for regularization.
result Regularizations enable Deep Autoencoders to better approximate data manifolds and generalize.
Unsupervised learning of phase transitions: from principal component analysis to variational autoencoderscond-mat.stat-mech
We employ unsupervised machine learning techniques to learn latent parameters which best describe states of the two-dimensional Ising model and the three-dimensional XY model. These methods range from principal component analysis to artificial neural network based variational autoencoders. The states are sampled using …
Proposes learning a hierarchical prior in VAEs to avoid over-regularization.
problem Over-regularization in VAEs with standard normal priors.
method Formulates as a constrained optimisation problem, introduces graph-based interpolation.
result Learned latent representation reflects data manifold topology and properties.
This paper clarifies VAE's property through geometric and information-theoretic interpretations.
problem The transparency of VAE model is an underlying issue.
method Quantitative understanding of VAE through differential geometry and information theory.
result VAE can be mapped to an implicit isometric embedding with a scale factor derived from the posterior parameter.
Autoencoder neural networks reconstruct missing indoor environment data.
problem Missing data in building operation data sets.
method Three different autoencoder neural networks trained to reconstruct missing data.
result Reconstructing variables with average RMSEs of 0.42 °C, 1.30 % and 78.41 ppm.
This paper reviews and benchmarks DVAEs for sequential data.
problem Processing sequential data with temporal dependencies.
method Dynamical Variational Autoencoders (DVAEs) for sequential data.
result Experimental benchmark on speech analysis-resynthesis task.
Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencodersphysics.chem-ph
GMVAE improves clustering in molecular simulations data.
problem Clustering metastable states in multi-basin free-energy landscapes.
method Gaussian mixture variational autoencoder (GMVAE) for dimensionality reduction and clustering.
result Enhanced clustering of metastable states compared to standard VAEs.
Model disentangles timbre and pitch for musical instruments.
problem Learning disentangled representations of musical instrument sounds.
method Gaussian mixture variational autoencoders with two separate encoders for timbre and pitch.
result Model successfully disentangles timbre and pitch, enabling controllable synthesis and transfer.
A Frequentist Statistical Introduction to Variational Inference, Autoencoders, and Diffusion Modelsstat.ML
This paper bridges statistical and machine learning approaches to variational inference.
problem Statisticians struggle to understand variational inference from a Frequentist perspective.
method Explains VI, VAEs, and DDMs from a Frequentist viewpoint, starting with EM.
result VI emerges as a scalable solution for intractable E-steps in VAEs and DDMs.
X-VAE uses data-adaptive Gaussian priors to improve latent space modeling.
problem Limitations of standard Gaussian priors in complex datasets.
method Data-adaptive Gaussian prior derived from pretrained autoencoder latent codes.
result Improved latent space modeling and generation quality.
CLWF improves time series imputation speed and accuracy.
problem Slow convergence in diffusion model-based imputation methods.
method CLWF uses Lagrangian mechanics to learn velocity and integrates a denoising autoencoder to estimate gradient.
result CLWF outperforms state-of-the-art imputation approaches.
Paper improves molecular property prediction using denoising autoencoders.
problem Limited data for molecular property prediction from 3D structures.
method Pre-training via denoising for learning molecular force fields.
result Achieves new state-of-the-art performance on QM9 dataset.
In this paper, we introduce an algorithm for performing spectral clustering efficiently. Spectral clustering is a powerful clustering algorithm that suffers from high computational complexity, due to eigen decomposition. In this work, we first build the adjacency matrix of the corresponding graph of the dataset. To bui…
A new method for the unsupervised learning of sparse representations using autoencoders is proposed and implemented by ordering the output of the hidden units by their activation value and progressively reconstructing the input in this order. This can be done efficiently in parallel with the use of cumulative sums and …
Piano Geniecs.LG
Piano Genie lets non-musicians improvise on a piano.
problem Improvising on the piano for non-musicians.
method Trained recurrent neural network autoencoders with discrete bottlenecks to learn mappings between user inputs and piano pieces.
result Piano Genie allows users to improvise on the piano with musically meaningful constraints.
Method reconstructs aneurysm growth history from patient parameters using physics-informed autoencoder.
problem Predicting arterial aneurysm rupture due to inaccessible growth time series.
method Physics-informed autoencoder combined with neural network for mapping patient parameters to aneurysm growth time history.
result Incorporating physical model constraints improves time series reconstruction, especially in noisy data.
Gradient descent on LSE objectives implicitly performs EM, leading to collapse without volume control.
problem Gradient collapse in autoencoders without volume control.
method Introduced a single-layer encoder with an LSE objective and InfoMax regularization for volume control.
result Gradient--responsibility identity holds exactly; LSE alone collapses; variance prevents dead components; decorrelation prevents redundancy.
Method trains multi-modal policy from unlabeled mixed demonstrations.
problem Training policies from unlabeled mixed demonstrations.
method Variational autoencoder with categorical latent variable to discover latent factors of variation.
result Policy can reproduce specific behaviors by conditioning on categorical vectors.
ES-VAE models skeletal pose trajectories by removing nuisance factors.
problem Handling camera orientation, subject scale, viewpoint, and execution speed in skeletal data.
method ES-VAE uses TSRVF representation on Kendall's shape manifold to isolate shape dynamics.
result ES-VAE outperforms standard VAEs and sequence modeling baselines in gait cycle prediction and action recognition.
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…