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

5 results for “Cross-comparison”

Unique Metric for Health Analysis with Optimization of Clustering Activity and Cross Comparison of Results from Different Approachstat.ML

A new metric optimizes clustering and compares results from various methods.

problem Determining the right number of clusters and comparing different clustering methods.

method Proposes a novel metric to find the optimal number of clusters and compare different clustering techniques.

result Optimizes clustering and cross-comparison of results from different methods.

Clustering Metric Optimization Cross-comparison Clustering methods

2018-10-08abs ↗pdf ↗

Cross comparison and modelling of Goldman Sachs, Morgan Stanley, JPMorgan Chase, Bank of America, and Franklin Resourcesq-fin.GN

We have studied statistical characteristics of five share price time series. For each stock price, we estimated a best fit quantitative model for the monthly closing price as based on the decomposition into two defining consumer price indices selected from a large set of CPIs. It was found that there are two pairs of s…

2012-12-05abs ↗pdf ↗

GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Modelscs.LG

GeoShapley uses game theory to measure spatial effects in ML models.

problem Measuring the impact of location on machine learning model predictions.

method Extends Shapley value framework to quantify spatial effects in various ML models.

result Validated GeoShapley values against known processes and demonstrated utility in house price modeling.

game theory machine learning spatial effects model interpretation Shapley value

2023-12-06abs ↗pdf ↗

Parametric measures of variability induced by risk measuresq-fin.RM

We introduce and compare new variability measures based on risk quantiles.

problem Comparing variability measures in risk management.

method Developed a framework for one-parameter families of inter-Expected Shortfall differences and inter-expectile differences.

result Characterized symmetric and comonotonic variability measures as mixtures of inter-Expected Shortfall differences.

variability measures risk management Expected Shortfall quantile differences stochastic orders

2020-12-09abs ↗pdf ↗

The Mean Dimension of Neural Networks -- What causes the interaction effects?stat.ML

Estimates mean dimension of neural networks to reveal interaction effects.

problem Understanding interaction effects in neural networks.

method Estimation procedure for mean dimension from datasets, analyzing layer-by-layer evolution and impact of activation functions.

result Mean dimension reveals differences in interaction magnitude across neural network architectures.

mean dimension neural networks interaction effects convolutional architectures image recognition

2022-07-11abs ↗pdf ↗