A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets. To remove topological obstructions, we introduce Diffusion Variational Autoencoders with arbitrary manifolds as a latent space. A Diffusion Variational Autoencoder uses t…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “diffusion autoencoder”
PaGoDA reduces diffusion model training costs by 64x.
problem Diffusion models are computationally expensive during training.
method Three-stage pipeline: downsampled training, distillation, progressive super-resolution.
result PaGoDA achieves state-of-the-art performance with reduced training costs.
A new TTS method uses diffusion and VAE for better speech synthesis.
problem Improving text-to-speech synthesis for better speech quality and robustness.
method Combines diffusion probabilistic model and variational autoencoder for latent variable conversion.
result The method is robust to poor orthography and alignment errors.
SAMI learns disentangled representations from data.
problem Learning disentangled representations from data.
method Combines diffusion models and VAEs to learn disentangled representations.
result SAMI learns disentangled representations that are interpretable and useful.
VADD enhances discrete diffusion models by capturing inter-dimensional correlations, improving sample quality.
problem Limited modeling of inter-dimensional dependencies in MDMs degrades performance with few denoising steps.
method Introduces an auxiliary recognition model for latent variable modeling, enabling stable training via variational lower bounds maximization and amortized inference.
result VADD consistently outperforms MDM baselines in sample quality with few denoising steps.
Paper uses autoencoders for efficient reduced-order modeling of eigenvalue problems.
problem Efficiently modeling eigenvalue problems in high dimensions.
method Autoencoder-based reduced-order modeling for eigenvalue problems.
result Autoencoder-based models outperform standard POD-Galerkin methods in neutron diffusion applications.
Diffusion Autoencoders with Perceivers for Long, Irregular and Multimodal Astronomical Sequencesstat.ML
daep learns from irregular, multimodal astronomical data.
problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.
CoVAE improves VAEs by reducing training steps and improving quality.
problem Two-stage training overhead and increased sampling times.
method Consistency training of VAEs with progressive latent representations and time-dependent β parameter.
result CoVAE generates high-quality samples in one or few steps.
Improved image compression with diffusion models outperforming state-of-the-art methods.
problem Difficulties in replicating text-to-image success in image compression.
method Two-stage approach combining autoencoder targeting MSE followed by score-based decoder.
result Significantly improved perceptual quality at a given bit-rate, measured by FID score.
Paper proposes a method to monitor research topic evolution.
problem Difficulty in tracking research topic diffusion and evolution.
method Deep Non-negative Autoencoder with information divergence measurement.
result Identifies evolution of research topics and discovers topic diffusions.
Diffusion models generate music sequences without autoregressive loops.
problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.
EDG generates Boltzmann samples from latent variables efficiently.
problem Sampling from complex energy functions in high dimensions.
method Combines variational autoencoders and diffusion models; uses a decoder and diffusion-based encoder.
result EDG outperforms existing methods in various sampling tasks.
DiffEnc improves diffusion models by adding flexibility and achieving better likelihood on CIFAR-10.
problem Improving the likelihood of diffusion models on image datasets.
method Introducing a data- and depth-dependent mean function and a free weight parameter for noise variance.
result Achieved statistically significant improvement in likelihood on CIFAR-10.
A new method uses hyperspherical latent spaces to disentangle data with periodic structures.
problem Disentangling data with periodic or cyclic underlying factors in Euclidean space.
method Diffusion Variational Autoencoder with a modified Evidence Lower Bound.
result The method can recover periodic true factors effectively.
A new model trains prior and encoder/decoder networks simultaneously for efficient generation.
problem Complex autoregressive prior in VQ-VAE models leads to slow generation.
method Builds a diffusion bridge between continuous and non-informative prior distributions.
result Model is competitive and efficient in optimization and sampling.
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.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
GeoFunFlow: Geometric Function Flow Matching for Inverse Operator Learning over Complex Geometriescs.LG
GeoFunFlow tackles inverse problems on complex geometries with efficient learning.
problem Challenges in inverse problems governed by PDEs, especially on irregular geometries.
method Combines geometric function autoencoder and latent diffusion model trained via rectified flow.
result Achieves state-of-the-art reconstruction accuracy and efficient inference.
FunDiff models physical functions using diffusion and autoencoders.
problem Adapting generative models to continuous physical functions.
method Combines latent diffusion with function autoencoder, enforcing physical priors.
result Achieves optimal convergence rates for physical function estimation.
LION generates high-quality 3D shapes using hierarchical latent diffusion models.
problem Creating high-quality 3D shapes for digital artists.
method Hierarchical Latent Point Diffusion Model (LION) with a global shape latent and point-structured latent space.
result LION achieves state-of-the-art generation performance on ShapeNet benchmarks.
Improved deep hierarchical VAE with diffusion-based VampPrior.
problem Latent variable generative modeling challenges.
method Hierarchical VAE with amortized diffusion-based VampPrior.
result Better performance with fewer parameters and improved stability.
Variational autoencoders (VAEs) and generative adversarial networks (GANs) enjoy an intuitive connection to manifold learning: in training the decoder/generator is optimized to approximate a homeomorphism between the data distribution and the sampling space. This is a construction that strives to define the data manifo…
Combines deep state space models with diffusion models for better forecasting and capturing latent dynamics
problem Forecasting and capturing latent dynamics in time series
method DDSSM: Diffusion-driven state space model
result Empirically outperforms state-of-the-art deep SSM
Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscs.LG
Survey and clarify manifold-supported data in deep generative models.
problem Understanding why some DGMs succeed or fail at low-dimensional data.
method Formal analysis and new model connections.
result DGMs on autoencoder representations minimize Wasserstein distance.
Researchers calculate entropy of heat kernel on manifolds for very small times.
problem Estimating entropy of heat kernel on compact Riemannian manifolds for small times.
method Asymptotic expansion, polynomial expressions in curvature tensor components.
result First three coefficients of entropy expansion computed and expressed as polynomials.
CRATE-MAE learns structured representations from unlabeled data.
problem Learning structured representations from unlabeled data.
method Structured Diffusion with White-Box Transformers.
result CRATE-MAE achieves highly promising performance on large-scale imagery datasets.
CTSyn generates high-quality synthetic tabular data.
problem Challenges in generating high-quality synthetic tabular data.
method Diffusion-based generative foundation model with autoencoder and conditional latent diffusion.
result CTSyn outperforms existing table synthesizers on standard benchmarks.
Generates financial time series with stylized facts using diffusion models.
problem Generating realistic synthetic financial time series with statistical properties like fat tails, volatility clustering, and seasonality.
method Utilizes denoising diffusion probabilistic models (DDPMs) with wavelet transformation to convert and generate financial time series.
result Demonstrates that the proposed approach satisfies stylized financial time series properties.
Diffusion-VAE tackles multi-step stock price prediction with stochastic noise.
problem Challenges in multi-step stock price prediction due to stochasticity and target price sequence.
method Combines hierarchical VAE and diffusion probabilistic techniques for seq2seq stock prediction.
result D-Va model outperforms state-of-the-art solutions in prediction accuracy and variance.
GD-VAEs learn dynamics from observations using geometric and topological information.
problem Learning parsimonious representations of nonlinear dynamics from observations.
method Develops data-driven methods incorporating geometric and topological information using Variational Autoencoders (VAEs).
result GD-VAEs provide methods for learning reduced dimensional representations of nonlinear dynamics.
Antithetic noise improves diffusion models' uncertainty quantification.
problem Improving uncertainty quantification in diffusion models.
method Pairing each noise sample with its negation, leading to strong negative correlation.
result Substantially more reliable uncertainty quantification with up to 90% narrower confidence intervals.
A new method integrates autoencoders with geometry regularization for manifold learning.
problem Extracting simplified low-dimensional representations that capture intrinsic geometry in data.
method Integrates autoencoders with a geometric regularization term based on diffusion potential distances.
result The method preserves intrinsic structure, enables out-of-sample extension, and faithful reconstruction.
Early stopping improves sample quality in latent diffusion models.
problem Latent diffusion models degrade sample quality with conventional early stopping.
method Analyzed the interaction between latent dimension and stopping time under Gaussian framework.
result Lower-dimensional representations benefit from earlier termination, higher-dimensional spaces require later stopping.
The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatchcs.CV
SVHN dataset's split affects generative models but not digit classification.
problem Distribution mismatch between SVHN training and test sets impacts generative models.
method Empirically showed distribution mismatch affects generative models; proposed mixing and re-splitting.
result Distribution mismatch in SVHN dataset significantly impacts probabilistic generative models.
This paper investigates how synthetic data and overparameterization improve VAE generalization.
problem Improving generalization performance of Variational Autoencoders (VAEs).
method Investigates the effectiveness of synthetic data and overparameterization in VAEs.
result Training on synthetic data and using more parameters improves VAE generalization, inference, and robustness.
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.
New methods create counterfactuals for image regression models.
problem Creating interpretable explanations for regression models in images.
method Two methods using diffusion-based generative models to create counterfactuals.
result Diffusion-based methods produce realistic, semantic, and smooth counterfactuals.
In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose novelty detection methods based on training variational autoencoders…
Develops deep generative models for stratified learning.
problem Challenges in learning distributions on stratified spaces with varying dimensions and singularities.
method Two generative frameworks: sieve maximum likelihood and diffusion-based.
result Establishes convergence rates and consistency for estimating intrinsic dimensions and number of strata.
This paper tackles unsupervised speech enhancement using RVAE and proposes efficient sampling methods.
problem Unsupervised speech enhancement with high computational complexity.
method Recurrent variational autoencoder (RVAE) combined with Langevin dynamics and Metropolis-Hasting sampling.
result Sampling-based algorithms outperform VEM and achieve robust generalization.
A new diffusion model improves cryo-EM structure sampling.
problem Gaussian prior in VAE fails to match approximate posterior in cryo-EM data.
method Train a diffusion model as an expressive, learnable prior in cryoDRGN framework.
result Samples accurately follow the data distribution, not the VAE prior.
Unified framework reduces NFEs for inverse problems.
problem High computational costs and degraded reconstruction quality in existing LDM-based inverse solvers.
method Consistency Regularised Gradient Flows for posterior sampling and prompt optimization.
result Significantly reduced computational cost with state-of-the-art performance.
Imputation method respects manifold structure for missing data.
problem Missing data imputation in high-dimensional data.
method Model-based imputation using mixture variational autoencoders and sampling-importance-resampling (SIR).
result Competitive performance and uncertainty quantification in imputations.
RAE improves image representation learning with simplified design choices.
problem Improving image representation learning using pretrained vision encoders.
method Generalized RAE formulation, complementary working mechanisms of RAE and REPA, and free CFG guidance.
result RAEv2 achieves state-of-the-art results with 10x faster convergence and less training time.
DiffKnock improves feature selection in neural networks with complex dependencies and non-linear associations.
problem Selecting important features in neural networks with complex dependencies and non-linear associations.
method DiffKnock uses diffusion models to generate knockoffs and neural network statistics to measure feature importance.
result DiffKnock outperforms existing methods in detecting non-linear associations and preserving feature dependencies.
Diffusion Netsstat.ML
Non-linear manifold learning enables high-dimensional data analysis, but requires out-of-sample-extension methods to process new data points. In this paper, we propose a manifold learning algorithm based on deep learning to create an encoder, which maps a high-dimensional dataset and its low-dimensional embedding, and …
IntroVAC learns interpretable latent subspaces for better image quality.
problem Difficulties in interpreting latent spaces and limitations in image generation.
method Introspective Variational Classifier (IntroVAC) using additional labels and adversarial training.
result Improved image quality and meaningful latent directions for fine-grained manipulation.
This study rethinks the latent space in generative modeling, improving performance with less complex models.
problem Determining the optimal latent space for generative models and understanding its impact on model complexity.
method Proposed a new distance metric between latent and data distributions, and a two-stage training strategy called Decoupled Autoencoder (DAE).
result Improves generative performance with less complex models, as shown by comprehensive experiments on various models.