Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations

By Marcus Gawronsky, Chun-Sung Huang

Published 2026-08-30

Everscope rating

1550.1

Relevance to quantitative trading

8 / 10

Implementation complexity

7 / 10

Reproducibility

3 / 5

About this paper

Methodology: Information-Certified Portfolio Variance Bound via Wasserstein-2 Distributional Geometry. Problem types: Portfolio Optimization, Risk Management, Optimization, Density Estimation, Natural Language Processing.

arXiv:2608.29692 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.