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

6 results for “Welsch”

Robust matrix completion via Novel M-estimator Functionsstat.ML

New robust loss functions improve matrix completion accuracy.

problem Outliers in data corrupting matrix completion accuracy.

method Developed nonconvex M-estimator functions to down-weight outliers.

result Proposed methods outperform competitors in recovery accuracy and runtime.

matrix completion robustness outliers Welsch Cauchy

2023-10-08abs ↗pdf ↗

Robust X-Learner: Breaking the Curse of Imbalance and Heavy Tails via Robust Cross-Imputationstat.ML

Robust X-Learner improves HTE estimation in imbalanced and heavy-tailed data.

problem Estimating HTE in imbalanced and heavy-tailed data.

method Integrates γ-divergence objective and Proxy Hessian strategy into gradient boosting.

result Reduces PEHE metric by 98.6% in semi-synthetic Criteo Uplift dataset.

Heterogeneous Treatment Effects Imbalance Heavy Tails Robust Cross-Imputation γ-divergence

2026-01-21abs ↗pdf ↗

A General and Adaptive Robust Loss Functioncs.CV

We present a generalization of the Cauchy/Lorentzian, Geman-McClure, Welsch/Leclerc, generalized Charbonnier, Charbonnier/pseudo-Huber/L1-L2, and L2 loss functions. By introducing robustness as a continuous parameter, our loss function allows algorithms built around robust loss minimization to be generalized, which imp…

2017-01-11abs ↗pdf ↗

Bayesian X-Learner: Calibrated Posterior Inference for Heterogeneous Treatment Effects under Heavy-Tailed Outcomesstat.ML

Bayesian X-Learner calibrates uncertainty and robustness for CATE estimation under heavy-tailed data.

problem Estimating heterogeneous treatment effects with calibrated uncertainty and robustness to heavy-tailed outcomes.

method Bayesian X-Learner using cross-fitted doubly robust pseudo-outcomes and MCMC for a full posterior over CATE.

result Bayesian X-Learner achieves robust and calibrated CATE estimation on real and contaminated data.

Bayesian X-Learner CATE estimation Heterogeneous treatment effects Heavy-tailed outcomes Calibrated uncertainty

2026-04-30abs ↗pdf ↗

Stop Suppressing the Tail: Causal Inference for Extreme Eventsstat.ML

New method estimates extreme outcomes in heavy-tailed data, breaking circular dependence.

problem Estimating outcomes for extreme events in heavy-tailed data.

method Proposes an ADRF estimator that includes a structured tail-shape output and a diagnostic to evaluate tail shape.

result Successfully reduces MAE in deep-tail and conditional-shortfall predictions.

causal inference heavy-tailed data extreme events tail shape double machine learning

2026-05-26abs ↗pdf ↗

SHIFT: Robust Double Machine Learning for Average Dose-Response Functions under Heavy-Tailed Contaminationstat.ML

SHIFT improves robustness in estimating dose-response functions with heavy-tailed contamination.

problem Outliers bias estimates of average dose-response functions in heavy-tailed data.

method SHIFT combines cross-fit nuisance orthogonalization, Welsch-loss, and defensive OLS refit.

result SHIFT reduces RMSE from 1.03 to 0.33 on localized contamination test.

Dose-Response Functions Heavy-Tailed Contamination Robust Machine Learning Double Machine Learning Outlier Robustness

2026-04-30abs ↗pdf ↗