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

count % of corpus

3 results for “VAEAC”

Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Featuresstat.ML

Paper uses VAEAC to estimate Shapley values for complex models with mixed features.

problem Estimating Shapley values for models with dependent mixed features.

method Uses variational autoencoder with arbitrary conditioning (VAEAC) to model feature dependencies.

result VAEAC approach outperforms state-of-the-art methods for various settings.

Shapley values VAEAC Mixed features Predictive models Dependent data

2021-11-26abs ↗pdf ↗

Missing Features Reconstruction Using a Wasserstein Generative Adversarial Imputation Networkcs.LG

Paper proposes WGAIN for missing feature reconstruction.

problem Missing data in datasets.

method Wasserstein Generative Adversarial Imputation Network (WGAIN) compared to traditional methods.

result WGAIN outperforms traditional methods in imputing missing data.

missing data imputation generative adversarial networks Wasserstein classification accuracy

2020-06-21abs ↗pdf ↗

Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Modelscs.LG

AGMs outperform EGMs in generalizing to unseen inference tasks.

problem Training graphical models for inference tasks not seen during training.

method Adversarial training of an ensemble of discrete graphical models.

result AGMs significantly outperform EGMs in generalization to unseen tasks.

adversarial training inference graphical models generalization unsupervised learning

2020-07-09abs ↗pdf ↗