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

4999148197 · Jun 202019922001200920182026
48 results for Kendall's rank correlation

Improved portfolio optimization using Kendall-like correlation coefficients.

problem Accurate estimation of eigenvectors in data-poor regimes for portfolio optimization.
method Developed generalized correlation coefficients based on Kendall's rank correlation.
result Markowitz portfolios with lower out-of-sample risk using these coefficients.

New algorithm detects block-exchangeable structure in large correlation matrices.

problem Detecting hidden dependence patterns in large correlation matrices.
method Robust algorithm based on Kendall's rank correlation.
result The new estimator performs better than sample correlation matrices in structured cases.

Standardizes weighted ranking correlation coefficients to maintain zero expected value.

problem Measuring correlation between weighted rankings of items.
method Develops a standardization function g(·) that transforms coefficients to zero expected value under randomness.
result A general standardization function g(Γ) that preserves the domain [-1,1] and reduces to the identity for coefficients already satisfying zero-expected-value property.

This paper uses rank correlation methods to construct MSTs from financial returns, finding them more stable and robust.

problem Stability and robustness of MSTs constructed from financial correlation matrices.
method Pearson, Spearman, and Kendall's ττ rank correlation methods applied to daily financial returns.
result Rank MSTs are more stable and robust than MSTs constructed using Pearson correlation.

Kendall transformation converts continuous data into categorical vectors for robust information theory.

problem Handling small number of observations and preserving ranking in continuous data.
method Kendall transformation converts ordered features into categorical vectors of pairwise order relations.
result Kendall transformation makes information theory methods applicable to continuous data robustly.

The optimal ranking score between precision and recall is rarely F1 and can be found using specific methods.

problem Finding a meaningful and optimal compromise between precision and recall scores.
method Established a shortest path between precision- and recall-induced rankings, framed the problem as an optimization problem, and provided theoretical tools to find the optimal β.
result F1 and its skew-insensitive version are not optimal tradeoffs between precision and recall scores.

Network analysis reveals changing cryptocurrency market leaders.

problem Understanding evolving cryptocurrency market leaders and their influence.
method Hourly-resolution data and Kendall's Tau correlation for network analysis.
result Pearson's correlation underestimates market dynamics; FTT and FTX were key during the 2021 bull run.

New estimators reduce computation for Kendall's tau and conditional Kendall's tau matrices under structural assumptions.

problem Efficient estimation of Kendall's tau and conditional Kendall's tau matrices for large dimensions.
method Averaging pairwise estimates over blocks or conditional estimates, exploiting structural assumptions.
result Improved estimators with reduced computational cost and similar error level.

We propose a semiparametric approach, named nonparanormal skeptic, for estimating high dimensional undirected graphical models. In terms of modeling, we consider the nonparanormal family proposed by Liu et al (2009). In terms of estimation, we exploit nonparametric rank-based correlation coefficient estimators includin…

2012-06-27abs ↗pdf ↗

Study measures uncertainty in MST identification across different correlation networks.

problem Uncertainty in MST identification across various correlation-based market networks.
method Developed a framework using random variable networks (RVN) to measure uncertainty of MST identification.
result FDR is the most appropriate measure for MST identification reliability.

Permutation-valued features arise in a variety of applications, either in a direct way when preferences are elicited over a collection of items, or an indirect way in which numerical ratings are converted to a ranking. To date, there has been relatively limited study of regression, classification, and testing problems …

2016-03-25abs ↗pdf ↗

New findings challenge the importance of forecast accuracy in battery storage optimization, highlighting the role of rank correlation instead.

problem The challenge of optimizing battery storage dispatch decisions in multi-market electricity trading using forecast accuracy metrics.
method A hierarchical three-layer optimization system trading in multiple markets (FCR, aFRR, day-ahead, intraday) with real market data.
result Rank correlation (Kendall tau) is a better predictor of intraday dispatch value than forecast accuracy (MAE), with a threshold of tau around 0.85-0.95 capturing up to 97-100% of perfect-foresight revenue.

The paper proposes a method to model financial data asynchronously using copulas.

problem Modeling intraday financial returns of multiple assets due to asynchronous data.
method Proposes a consistent estimator of the correlation coefficient for Elliptical copulas and an improved estimator for non-elliptical copulas.
result The proposed estimator reduces bias in estimating copula parameters for a general class of copulas.

We propose a number of techniques for obtaining a global ranking from data that may be incomplete and imbalanced -- characteristics almost universal to modern datasets coming from e-commerce and internet applications. We are primarily interested in score or rating-based cardinal data. From raw ranking data, we construc…

2008-11-07abs ↗pdf ↗

New analysis shows interpretability doesn't guarantee steering utility in LLMs.

problem Does higher interpretability lead to better steering utility in large language models?
method Trained 90 SAEs across three LLMs, evaluated interpretability and steering utility, used Kendall's rank coefficients for analysis.
result Interpretability is only weakly associated with steering utility, and features selected by Delta Token Confidence improve steering performance.

New method for summarizing ranking distributions using consensus ranking distributions.

problem Summarizing ranking distributions efficiently and accurately.
method Introducing consensus ranking distributions and a top-down tree-structured statistical algorithm.
result Optimal distortion can be expressed as a function of pairwise probabilities, enabling efficient learning methods.

This paper tackles ranking preferences through local consensus, improving prediction accuracy.

problem Predicting individual preferences over a set of items based on observed characteristics.
method Proposes ranking median regression, introducing local consensus/median for efficient learning.
result Developed efficient methods for ranking median regression, achieving fast learning rates.

This paper improves autoregressive model training by focusing on test metrics, not just likelihood.

problem Training autoregressive models to perform better on specific metrics like METEOR score.
method Follows the learning-to-search approach, constructing a reference policy and choosing test metric-related costs.
result The standard KL loss only learns high-probability tokens and can be improved with ranking objectives.

The abstract shows how conditional Kendall's tau can be seen as a classification problem.

problem Estimating conditional Kendall's tau from random variables.
method Rewriting the problem as a classification task, proving consistency and asymptotic normality of estimators, adapting machine learning techniques.
result The consistency and asymptotic normality of penalized approximate maximum likelihood estimators.

In this paper, we propose a semiparametric approach, named nonparanormal skeptic, for efficiently and robustly estimating high dimensional undirected graphical models. To achieve modeling flexibility, we consider Gaussian Copula graphical models (or the nonparanormal) as proposed by Liu et al. (2009). To achieve estima…

2012-02-10abs ↗pdf ↗

New method detects spike-and-wave epileptiform discharges using Kendall's Tau-b.

problem Detecting spike-and-wave epileptiform discharges in EEG signals.
method Proposes a new method based on Kendall's Tau-b coefficient.
result High Specificity and rule in (SpPIn) for spike-and-wave discharge detection.

A new algorithm for parallel transport on shape spaces is presented and compared to existing methods.

problem Statistical analysis of shape data, especially in time series and optimization.
method Pole ladder algorithm for parallel transport on Kendall shape spaces, compared to integration methods.
result The pole ladder algorithm is a more efficient method for parallel transport.

The study identifies persistent motifs in stock correlations for sector-neutral portfolio diversification.

problem Forecasting and diversification of sector-neutral portfolios using long-term correlations.
method Analysis of Triangulated Maximally Filtered Graphs (TMFG) generated from rolling windows of stock price log-returns, identifying persistent motifs.
result Persistent motifs in stock correlations can be used to forecast and diversify sector-neutral portfolios, reducing volatility.

This paper proposes a new class of copulas which characterize the set of all twice continuously differentiable copulas. We show that our proposed new class of copulas is a new generalized copula family that include not only asymmetric copulas but also all smooth copula families available in the current literature. Spea…

2012-10-08abs ↗pdf ↗

New Hermite series estimator for Spearman rank correlation in non-stationary data.

problem Estimating time-varying Spearman rank correlation efficiently.
method Hermite series based sequential estimator for both stationary and non-stationary settings.
result Competitive performance compared to existing algorithms in simulations and real data.

The paper describes correlations of spectra for higher rank Anosov representations.

problem Understanding correlations of spectra for Anosov representations of higher rank groups.
method Relates correlation problem to counting projections in truncated hypertubes.
result Extends previous work on rank one representations to higher rank.

A new method for Gaussian Processes handles mixed continuous and categorical inputs.

problem Modeling cross-correlations between continuous and categorical data.
method Low-Rank Correlation (LRC) method for Gaussian Processes with flexible rank approximation.
result LRC outperforms existing methods in estimating cross-correlations and predicting response surfaces.

Proposes a method to enhance multi-view learning by maximizing higher order correlations.

problem Losing intrinsic interconnections among multiple views in pairwise correlation maximization.
method Formulates multi-view data as a low rank approximation problem using higher order correlation tensor and solves it with the generating polynomial method.
result Consistently outperforms prior methods on real multi-view data.