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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “re-fitting”

CLEAR: Covariant LEAst-square Re-fitting with applications to image restorationmath.ST

A new method to improve image restoration by re-fitting standard methods.

problem Systematic errors in popular restoration algorithms for image processing.

method Developing a re-fitting approach that preserves covariant information and Jacobian of original estimators.

result Improved image restoration results on numerical simulations.

image restoration covariant information re-fitting systematic errors affine transformation

2016-06-16abs ↗pdf ↗

Beyond the Smile: A Hybrid Convolutional VAE for Crypto Volatility Surfacescs.LG

A hybrid Convolutional VAE predicts crypto volatility surfaces, outperforming single-symbol approaches.

problem Predicting crypto volatility surfaces

method Convolutional VAE with hybrid predictor

result Model achieves 0.94-1.56 vol-point RMSE across BTC and ETH markets

crypto volatility VAE predictor reconstruction

2026-06-15abs ↗pdf ↗

Simultaneous Inference for Massive Data: Distributed Bootstrapstat.ML

Efficiently bootstraps massive distributed data without over-resampling.

problem Statistical inference for massive distributed data.

method Distributed Bootstrap applied to gradients from worker machines.

result Proves optimal statistical efficiency with minimal communication.

Bootstrap Distributed Computing Statistical Inference Massive Data

2020-02-19abs ↗pdf ↗

A Higher-Order Swiss Army Infinitesimal Jackknifemath.ST

A new method for approximating CV and bootstrap with higher-order infinitesimal jackknife.

problem Efficiently approximating cross-validation and bootstrap methods for machine learning.

method Higher-order infinitesimal jackknife (HOIJ) using Taylor series approximations and automatic differentiation.

result HOIJ provides higher-order accuracy and can be computed efficiently even in high dimensions.

infinitesimal jackknife higher-order approximation automatic differentiation cross-validation bootstrap

2019-07-28abs ↗pdf ↗

Iterative Least Trimmed Squares for Mixed Linear Regressioncs.LG

ILTS iteratively refines linear regression models on subsets of data.

problem Linear regression with corruptions and outliers.

method Iteratively selects and refits the subset of samples with lowest loss.

result ILTS converges linearly to the closest mixture component under certain conditions.

linear regression mixed linear regression corruptions subset selection iterative refinement

2019-02-10abs ↗pdf ↗

Approximate Cross-Validation in High Dimensions with Guaranteesstat.ML

A new method for fast, accurate cross-validation in high dimensions.

problem Efficiently approximating cross-validation in high-dimensional settings.

method A novel approximation method that works well in high dimensions, especially for sparse parameters.

result One approximation method performs well in high dimensions, with running time and error dependent on the support size.

cross-validation high dimensions approximation sparse parameters running time

2019-05-31abs ↗pdf ↗

Fast Uncertainty Quantification for Kernel-Based Estimators in Large-Scale Causal Inferencestat.ME

New method speeds up uncertainty estimation for large datasets in causal inference.

problem Computational infeasibility of bootstrap-based uncertainty quantification for large datasets.

method Extends cBLB algorithm to kernel methods, combining subsampling and resampling.

result Achieves computational scalability with nominal coverage.

kernel methods causal inference bootstrap large-scale data uncertainty quantification

2026-03-14abs ↗pdf ↗

Deep Integro-Difference Equation Models for Spatio-Temporal Forecastingstat.ML

Deep CNN models improve spatio-temporal forecasting efficiency.

problem Efficiently forecasting spatio-temporal dynamics with realistic models.

method Hierarchical statistical IDE framework with CNN for dynamic extraction.

result CNN provides accurate, interpretable, and computationally efficient forecasts.

spatio-temporal forecasting CNN IDE Kalman filter weather radar

2019-10-29abs ↗pdf ↗

Spectral Sparsification of Laplacian-Constrained Gaussian and Hüsler-Reiss Graphical Modelsstat.ME

Spectral sparsification improves Laplacian-constrained graph learning.

problem Improving accuracy of Laplacian-constrained graph learning.

method Spectral graph sparsification as a post-estimation operation.

result Improved accuracy of Laplacian-constrained graph learning.

spectral sparsification graph learning Laplacian-constrained graphical models

2026-06-15abs ↗pdf ↗