collaborators

5 papers

q-fin.PM2026

Joint Return and Risk Modeling with Deep Neural Networks for Portfolio Construction

Keonvin Park

Portfolio construction traditionally relies on separately estimating expected returns and covariance matrices using historical statistics, often leading to suboptimal allocation un…

cs.LG2025

PINT: Physics-Informed Neural Time Series Models with Applications to Long-term Inference on WeatherBench 2m-Temperature Data

Keonvin Park, Jisu Kim, Jaemin Seo

This paper introduces PINT (Physics-Informed Neural Time Series Models), a framework that integrates physical constraints into neural time series models to improve their ability to…

cs.LG2025

Towards a Foundation Model for Physics-Informed Neural Networks: Multi-PDE Learning with Active Sampling

Keon Vin Park

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs) by embedding physical laws into neural network train…

cs.LG2025

AL-PINN: Active Learning-Driven Physics-Informed Neural Networks for Efficient Sample Selection in Solving Partial Differential Equations

Keon Vin Park

Physics-Informed Neural Networks (PINNs) have emerged as a promising approach for solving Partial Differential Equations (PDEs) by incorporating physical constraints into deep lear…

cs.LG2025

Optimizing Portfolio Performance through Clustering and Sharpe Ratio-Based Optimization: A Comparative Backtesting Approach

Keon Vin Park

Optimizing portfolio performance is a fundamental challenge in financial modeling, requiring the integration of advanced clustering techniques and data-driven optimization strategi…