Research
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.

169,291 papers · 148 categories

Trend · papers per month

85170255340 · Jun 202019922001200920182026
48 results for Statistical distances

Paper proposes Gini distance statistics for estimating feature-label dependence.

problem Identifying statistical dependence between features and categorical labels.
method Generalized Gini distance in RKHS for feature-label dependence estimation.
result Gini distance statistics converge faster and have tighter error bounds than distance covariance.

The paper introduces a statistical distance matrix for better feature representation and clustering.

problem Lack of detailed distance representation between feature elements.
method Extended traditional statistical distance to a matrix form (statistical distance matrix) and applied hierarchical clustering.
result The statistical distance matrix with clustering (Information Mandala) provides clearer and geometrically arranged feature representations.

New statistical Minkowski distances for Gaussian mixtures with closed-form formulas.

problem Computing distances for Gaussian mixture models efficiently.
method Proposed novel statistical distances based on Minkowski's inequality for Gaussian mixtures.
result Closed-form formula for Gaussian mixture models with integer exponents.

This paper connects Wasserstein distances to MMD norms for compressive statistical learning.

problem Comparing and controlling Wasserstein distances between probability distributions.
method Establishing conditions under which Wasserstein distances can be controlled by MMD norms.
result Introducing Wasserstein regularity for compressive statistical learning.

Valid inference method for DTW distance for abnormal time-series detection.

problem Statistical inference on DTW distance under uncertain conditions.
method Conditional selective inference framework to derive valid p-values.
result First method to provide valid p-values for DTW distance.

New method connects distance and kernel tests for better data structure.

problem Connecting distance and kernel methods for hypothesis testing.
method Proposes a new bijective transformation between metrics and kernels.
result Distance methods can be exactly the same as kernel methods for sample statistics and p-value.

New smoothing technique improves Wasserstein distance estimation in high dimensions.

problem Estimating statistical distances between high-dimensional distributions.
method Gaussian smoothing of pp-Wasserstein distance and analysis of its asymptotic behavior.
result Gaussian-smoothed pp-Wasserstein distance converges at rate n1/2n^{-1/2}, improving over n1/dn^{-1/d} for unsmoothed distances.

High dimensional structured data such as text and images is often poorly understood and misrepresented in statistical modeling. The standard histogram representation suffers from high variance and performs poorly in general. We explore novel connections between statistical translation, heat kernels on manifolds and gra…

2012-06-20abs ↗pdf ↗

Generalizes robust statistics to various perturbations under Wasserstein distance.

problem Robust statistics for datasets corrupted by various perturbations.
method Generalizes robust statistics to any Wasserstein distance, showing robust estimation under certain perturbations.
result Generalized resilience property holds under moment or hypercontractive conditions, simplifying and improving known results.

This work improves understanding of projection robust optimal transport distances.

problem Understanding the behavior of minimum Wasserstein estimators in high-dimensional and misspecified models.
method Adopting projection robust (PR) optimal transport, establishing statistical properties, proposing IPRW distance, and providing asymptotic guarantees.
result Established fundamental statistical properties and proposed new distances that outperform Wasserstein distances empirically.

A new distance metric compares probability distributions using kernel covariance operators.

problem Comparing probability distributions in machine learning tasks.
method Introduces a novel distance metric based on Schatten norm of kernel covariance operators.
result The new distance metric is more discriminative and robust to hyperparameters.

Exact inference method for Wasserstein distance with finite-sample coverage.

problem Asymptotic approximation methods for Wasserstein distance lack finite-sample validity.
method Selective Inference inspired approach for exact inference.
result Valid confidence interval for Wasserstein distance with finite-sample coverage.

The article proposes modified Gower's coefficients for handling mixed type variables in nearest neighbor methods.

problem Handling mixed type variables in nearest neighbor methods, especially imputation and statistical matching.
method Suggests modifications to the Gower's distance for interval and ratio scaled variables to address unbalanced contributions and outlier sensitivity.
result Improved distance calculations reduce the unbalanced contribution of different variable types and attenuate outlier effects.

This paper provides performance guarantees for neural estimation of statistical distances.

problem Developing performance guarantees for neural estimation of statistical distances.
method Non-asymptotic error bounds using function approximation theorems and empirical process theory.
result Established a fundamental tradeoff between approximation and estimation errors in neural estimation of statistical distances.

This work provides guaranteed bounds on the total variation distance for univariate mixtures.

problem Lack of closed-form expressions for total variation distance between mixtures.
method Two methods: information monotonicity for lower bounds and geometric envelopes for upper bounds.
result Demonstrated tightness of bounds on Gaussian, Gamma, and Rayleigh mixtures.

Paper proposes new metrics to compare asset pricing models, incorporating Bayesian insights.

problem Power problems of statistical tests and misuse of alpha-based statistics.
method Unified set of distance-based performance metrics derived from alphas and standard errors, Bayesian interpretation of model performance.
result Bayesian approach favors models with low alpha dispersion and high explanatory power, especially the momentum factor.

Survey on closed-form Fisher-Rao distance expressions.

problem Finding closed-form expressions for Fisher-Rao distance.
method Collect and present examples of closed-form expressions for Fisher-Rao distance of discrete and continuous distributions.
result Presentation of closed-form expressions for Fisher-Rao distance of various distributions.

This thesis improves kernel-based distances for statistical inference and integration.

problem Efficiently measuring distances between probability distributions for robust and smooth modeling.
method Kernel-based distances, focusing on maximum mean discrepancy (MMD) and novel kernel quantile discrepancies.
result Improved MMD estimators for simulation-based inference and conditional expectations.

A new ABC technique using Sliced-Wasserstein distance improves inference quality.

problem Intractable likelihood in generative models leads to loss of information in summary statistics.
method Proposes Sliced-Wasserstein ABC, a new ABC technique based on the Sliced-Wasserstein distance.
result Derives theoretical consistency results and demonstrates improved performance on synthetic and image denoising tasks.

New measures quantify mutual dependence between multiple random vectors.

problem Measuring mutual dependence between multiple random vectors.
method Proposes three measures based on generalized distance covariance.
result Empirical and simplified empirical measures effectively test mutual independence.

A new robust Wasserstein distance is proposed to handle outliers in probability distributions.

problem Outliers in probability distributions make Wasserstein distances sensitive and impractical.
method Introduces a new outlier-robust Wasserstein distance Wpε\mathsf{W}_p^\varepsilon.
result Achieves strong robust estimation guarantees under the Huber ε\varepsilon-contamination model.

Improved computational efficiency for estimating Wasserstein distance.

problem Inefficient computation of Wasserstein distance for large samples.
method Developed Sample-Sketch-Solve paradigm using grid sketches.
result Approximates Wasserstein distance within ε error in ε^(-max(2, (d+1+o(1))/(1+α))) time.

Generative model learns molecular geometry from graph representations.

problem Generating equilibrium states for molecular systems is computationally expensive.
method Probabilistic model based on Euclidean distance geometry.
result Generative model achieves state-of-the-art accuracy in molecular conformation generation.

BDC uses Distance Correlation for efficient Bayesian optimization of expensive functions.

problem Efficiently optimizing expensive black-box functions with Bayesian methods.
method Integrates Bayesian optimization with Distance Correlation for automatic exploration and exploitation.
result BDC performs similarly to popular BO methods on benchmark tests and real terrain optimization.