Yield Curve Dynamics Using Variational Autoencoders Under No-arbitrage

By Fusheng Luo, Hélyette Geman

Published 2026-07-07

Everscope rating

1593.2

Relevance to quantitative trading

9 / 10

Implementation complexity

9 / 10

Reproducibility

3 / 5

About this paper

Methodology: Physics-Informed Two-Stage Generative Framework (CVAE_sT+LS + No-Arbitrage Neural SDE). Problem types: Time Series Forecasting, Generative Modeling, Dimensionality Reduction, Risk Management, Density Estimation, Unsupervised Learning, Structured Prediction, Portfolio Optimization, Anomaly Detection.

arXiv:2605.12764 · Paper rankings

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