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

count % of corpus

3 results for “pseudo-features”

Cavity Filling: Pseudo-Feature Generation for Multi-Class Imbalanced Data Problems in Deep Learningcs.LG

Method generates pseudo-features to balance imbalanced data.

problem Imbalanced data in deep learning problems.

method Generate pseudo-features from feature maps, augment minor-class data.

result Improves deep learning performance in imbalanced data problems.

deep learning imbalanced data pseudo-features cavity filling

2018-07-17abs ↗pdf ↗

ET-Lasso: A New Efficient Tuning of Lasso-type Regularization for High-Dimensional Datastat.ML

ET-Lasso improves Lasso feature selection in high-dimensional data.

problem Challenges in feature selection consistency of Lasso in high-dimensional data.

method ET-Lasso uses pseudo-features to separate active and inactive features by adding permuted features.

result ET-Lasso effectively selects active features under various scenarios.

Lasso regularization high-dimensional data feature selection pseudo-features false discovery rate

2018-10-10abs ↗pdf ↗

Transfer Learning with Deep Tabular Modelscs.LG

Deep tabular models outperform GBDT in medical diagnosis tasks.

problem Transfer learning for tabular data in medical diagnosis.

method Proposes a pseudo-feature method for transfer learning between different feature sets.

result Tabular neural networks outperform GBDT in medical diagnosis tasks.

transfer learning tabular data medical diagnosis neural networks gradient boosted decision trees

2022-06-30abs ↗pdf ↗