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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “bias-variance-covariance”

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Modelscs.LG

The paper introduces a new framework to assess generative model uncertainty.

problem Lack of a theoretical framework for assessing generative models' generalization and uncertainty.

method Bias-variance-covariance decomposition for kernel scores, with unbiased and consistent estimators.

result Kernel-based variance and entropy for uncertainty estimation are more predictive than existing methods.

generative models bias-variance-covariance kernel scores uncertainty estimation image generation

2023-10-09abs ↗pdf ↗

Multi-Head Attention as Ensemble Nadaraya-Watson Estimation: Variance Reduction, Decorrelation, and Optimal Head Diversitystat.ML

New theory shows how multi-head attention reduces variance and decorrelates outputs.

problem Understanding and optimizing multi-head attention in neural networks.

method Developed a statistical theory linking multi-head attention to ensemble Nadaraya-Watson estimators.

result MHA variance reduction depends on head decorrelation, not just head count.

multi-head attention Nadaraya-Watson variance reduction decorrelation head diversity

2026-05-18abs ↗pdf ↗