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.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

11 results for “IVA”

Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAEstat.ML

New method prevents posterior collapse in iVAE models.

problem Posterior collapse in iVAE models where observations and ICs are independent given covariates.

method Developed CI-iVAE by considering a mixture of encoder and posterior distributions in the objective function.

result Prevents posterior collapse, resulting in latent representations with more information of the observations.

iVAE posterior collapse covariate-informed representation learning variational autoencoder

2022-02-09abs ↗pdf ↗

Independent Vector Analysis: Identification Conditions and Performance Boundscs.LG

Recently, an extension of independent component analysis (ICA) from one to multiple datasets, termed independent vector analysis (IVA), has been the subject of significant research interest. IVA has also been shown to be a generalization of Hotelling's canonical correlation analysis. In this paper, we provide the ident…

2013-03-29abs ↗pdf ↗

Development of ICA and IVA Algorithms with Application to Medical Image Analysisstat.ML

Develops flexible ICA and IVA algorithms for medical image analysis.

problem Improper estimation of PDF leads to deviation from theoretical optimality.

method Flexible ICA and IVA algorithms using effective PDF estimation and sparsity.

result Unified mathematical framework for statistical independence and sparsity.

ICA IVA medical image analysis PDF estimation sparsity

2018-01-25abs ↗pdf ↗

Independent Vector Analysis with Deep Neural Network Source Priorseess.AS

Paper improves speech separation by using deep neural networks for more accurate density priors.

problem Improving the accuracy of source priors for independent vector analysis in speech separation.

method Estimating the derivative of speech density using deep neural networks to optimize performance indices.

result Neural network density priors outperform previous ones in convergence speed and SIR.

Independent Vector Analysis Deep Neural Networks Speech Separation Density Priors Convolutive Mixtures

2020-08-23abs ↗pdf ↗

Identifying through Flows for Recovering Latent Representationscs.LG

iFlow improves latent representation recovery by directly maximizing marginal likelihood.

problem Recovering true latent representations from observed data.

method Flow-based model (iFlow) that directly maximizes the marginal likelihood, providing theoretical guarantees on identifiability.

result iFlow delivers optimal solutions in both theory and practice, outperforming variational autoencoders.

latent representation flow-based model identifiability marginal likelihood variational autoencoder

2019-09-27abs ↗pdf ↗

Sampling Using Neural Networks for colorizing the grayscale imagescs.GR

This paper explores neural networks for colorizing grayscale images.

problem Colorizing grayscale images using neural networks.

method Comparison of existing and novel generative models (CVAE, CWGAN-GP, AGE, IVAE) trained on CIFAR-10 images.

result CVAE with L1 reconstruction loss and IVAE achieve the highest Inception Score (IS).

Neural Networks Colorization Grayscale Images Generative Models CIFAR-10

2018-12-27abs ↗pdf ↗

Independent Vector Analysis for Data Fusion Prior to Molecular Property Prediction with Machine Learningstat.ML

A new method uses IVA to fuse diverse molecular features for better machine learning predictions.

problem Challenges in selecting features for accurate molecular property prediction.

method Independent Vector Analysis (IVA) for fusing multiple molecular feature vectors into a single, compact set.

result Improved prediction performance of regression models for molecular properties.

Independent Vector Analysis Feature Fusion Molecular Property Prediction Machine Learning Quantum Chemistry

2018-11-01abs ↗pdf ↗

Conditionally Identifiable Latent Representation for Multivariate Time Series with Structural Dynamicscs.LG

Proposes iVDFM for identifying latent factors in multivariate time series.

problem Identifying latent factors in multivariate time series with structural dynamics.

method Identifiable Variational Dynamic Factor Model (iVDFM) with iVAE-style conditioning.

result Identifiable latent factors up to permutation and component-wise affine transformations.

Latent Factors Multivariate Time Series Structural Dynamics Identifiability Variational Inference

2026-03-24abs ↗pdf ↗

Indeterminacy in Generative Models: Characterization and Strong Identifiabilitystat.ML

New framework identifies strongly identifiable models from flexible generators.

problem Indeterminacies in generative models that prevent unique latent codes.

method Theoretical framework for analyzing latent variable models, excluding certain indeterminacies.

result Strong identifiability possible even with flexible nonlinear generators.

Generative models Identifiability Latent variable models Variational autoencoder Strong identifiability

2022-06-02abs ↗pdf ↗

Multidataset Independent Subspace Analysis with Application to Multimodal Fusionstat.ML

MISA combines multiple datasets for better feature extraction.

problem Combining diverse datasets for better feature extraction.

method MISA combines multiple heterogeneous datasets using Kotz distribution and combinatorial optimization.

result MISA produces robust generalization of ICA, IVA, and ISA.

multidataset subspace analysis blind source separation multimodal fusion Kotz distribution

2019-11-11abs ↗pdf ↗

Causal Mediation Analysis with Multi-dimensional and Indirectly Observed Mediatorscs.LG

New method handles indirect mediators in CMA for complex scenarios.

problem Handling indirect and multi-dimensional mediators in causal mediation analysis.

method Identifiable Variational Autoencoder (iVAE) architecture for multi-dimensional, indirectly observed mediators.

result Accurate estimation of direct and mediated effects in synthetic and semi-synthetic experiments.

Causal mediation analysis Indirect mediators Multi-dimensional Identifiable variational autoencoder Disentangled representation

2023-06-13abs ↗pdf ↗