Semantic Knowledge Technologies: what the Semantic Web lost sight of, and what it never had
本文指出了语义网未能实现机器可解释信息的目标，提出通过增加条件、操作基础和覆盖声明来完善，并命名为语义知识技术。
0 citationsRead paper
Selected work
Representative Papers
Robust Hedging Valuation Adjustment for Deep Hedging Policies under Market Frictions
This study proposes a unified framework that integrates robust hedging valuation adjustment (HVA), funding costs, and margin add-ons to assess the feasibility and risk reserves of derivative hedging strategies under transaction costs and market frictions. The approach constructs an uncertainty set via Kullback–Leibler divergence, incorporates a common stress tilt, and jointly optimizes the conditional value-at-risk (CVaR) of tracking loss—marking the first integration of these three adjustment components within a single robust optimization framework. Coupled with deep reinforcement learning and hedging simulations, the model favors wide-gamma classical hedging bands in high- and medium-liquidity markets but shifts toward sparse execution strategies under low liquidity. Under relaxed budget constraints, it consistently adopts broader hedging bands, significantly enhancing internal consistency and practical applicability.
0 citationsRead paper
Robust Hedging Valuation Adjustment under Liquidity--Demand Stress
This study addresses the trade-off between rebalancing costs and hedging error risk under liquidity constraints in dynamic hedging. The authors propose a robust methodology for quantifying Hedging Valuation Adjustment (HVA) by simulating rebalancing and unwinding trades under a no-trade band policy, constructing the resulting loss distribution, and optimizing the worst-case expected loss within a relative entropy uncertainty set—considering both fixed-radius and fixed-reference-stress specifications. Their analysis demonstrates that the width of the no-trade band significantly influences turnover, costs, and risk: while wider bands reduce transaction costs, they concurrently increase hedging error. This framework provides both theoretical grounding and a practical tool for implementing robust hedging strategies in liquidity-constrained environments.
0 citationsRead paper
Environmental CVA with K-Robust Wrong-Way Risk
This study addresses the absence of an operational framework for effectively translating long-term environmental scenarios into counterparty credit risk metrics suitable for pricing and regulatory capital calculations. It proposes the first integrated framework—Environmental Credit Valuation Adjustment (Environmental CVA)—that jointly incorporates climate and nature-related factors. The approach maps environmental scenario drivers to default intensity, introduces ecosystem-specific tail generators to quantify scenario model risk, and employs Kullback–Leibler divergence-based distributionally robust optimization to account for directional model misspecification risk. Empirical results demonstrate that different ecosystem generators yield significantly divergent nature-related CVA estimates, revealing a linkage mechanism through which climate and nature risks co-propagate. These findings underscore the necessity and efficacy of an integrated Environmental CVA assessment framework.
0 citationsRead paper
Differential Machine Learning for 0DTE Options with Stochastic Volatility and Jumps
This study addresses the insufficient accuracy and computational efficiency in pricing zero-day-to-expiration (0DTE) options and computing their Greeks under stochastic volatility with jumps. To overcome these limitations, the authors propose a differential machine learning approach that employs a single neural network to jointly output option prices and Greeks, integrating supervised signals from both prices and Greeks with residual regularization based on the underlying partial integro-differential equation (PIDE). The method features a novel three-stage training strategy, introduces a dedicated jump operator network to enhance identifiability of the jump component, and adopts a maturity-gated Black–Scholes parametrization for the price function. Numerical experiments under the Bates model demonstrate that the proposed framework achieves comparable pricing errors while significantly improving jump modeling fidelity and Greek accuracy, enabling stable intraday Delta hedging strategies and offering substantially faster computation than Fourier-based benchmarks.
0 citationsRead paper
Recent publications
Latest Papers
Semantic Knowledge Technologies: what the Semantic Web lost sight of, and what it never had
本文指出了语义网未能实现机器可解释信息的目标，提出通过增加条件、操作基础和覆盖声明来完善，并命名为语义知识技术。
0 citationsRead paper
Robust Hedging Valuation Adjustment for Deep Hedging Policies under Market Frictions
This study proposes a unified framework that integrates robust hedging valuation adjustment (HVA), funding costs, and margin add-ons to assess the feasibility and risk reserves of derivative hedging strategies under transaction costs and market frictions. The approach constructs an uncertainty set via Kullback–Leibler divergence, incorporates a common stress tilt, and jointly optimizes the conditional value-at-risk (CVaR) of tracking loss—marking the first integration of these three adjustment components within a single robust optimization framework. Coupled with deep reinforcement learning and hedging simulations, the model favors wide-gamma classical hedging bands in high- and medium-liquidity markets but shifts toward sparse execution strategies under low liquidity. Under relaxed budget constraints, it consistently adopts broader hedging bands, significantly enhancing internal consistency and practical applicability.
0 citationsRead paper
Robust Hedging Valuation Adjustment under Liquidity--Demand Stress
This study addresses the trade-off between rebalancing costs and hedging error risk under liquidity constraints in dynamic hedging. The authors propose a robust methodology for quantifying Hedging Valuation Adjustment (HVA) by simulating rebalancing and unwinding trades under a no-trade band policy, constructing the resulting loss distribution, and optimizing the worst-case expected loss within a relative entropy uncertainty set—considering both fixed-radius and fixed-reference-stress specifications. Their analysis demonstrates that the width of the no-trade band significantly influences turnover, costs, and risk: while wider bands reduce transaction costs, they concurrently increase hedging error. This framework provides both theoretical grounding and a practical tool for implementing robust hedging strategies in liquidity-constrained environments.
0 citationsRead paper
Environmental CVA with K-Robust Wrong-Way Risk
This study addresses the absence of an operational framework for effectively translating long-term environmental scenarios into counterparty credit risk metrics suitable for pricing and regulatory capital calculations. It proposes the first integrated framework—Environmental Credit Valuation Adjustment (Environmental CVA)—that jointly incorporates climate and nature-related factors. The approach maps environmental scenario drivers to default intensity, introduces ecosystem-specific tail generators to quantify scenario model risk, and employs Kullback–Leibler divergence-based distributionally robust optimization to account for directional model misspecification risk. Empirical results demonstrate that different ecosystem generators yield significantly divergent nature-related CVA estimates, revealing a linkage mechanism through which climate and nature risks co-propagate. These findings underscore the necessity and efficacy of an integrated Environmental CVA assessment framework.
0 citationsRead paper
Differential Machine Learning for 0DTE Options with Stochastic Volatility and Jumps
This study addresses the insufficient accuracy and computational efficiency in pricing zero-day-to-expiration (0DTE) options and computing their Greeks under stochastic volatility with jumps. To overcome these limitations, the authors propose a differential machine learning approach that employs a single neural network to jointly output option prices and Greeks, integrating supervised signals from both prices and Greeks with residual regularization based on the underlying partial integro-differential equation (PIDE). The method features a novel three-stage training strategy, introduces a dedicated jump operator network to enhance identifiability of the jump component, and adopts a maturity-gated Black–Scholes parametrization for the price function. Numerical experiments under the Bates model demonstrate that the proposed framework achieves comparable pricing errors while significantly improving jump modeling fidelity and Greek accuracy, enabling stable intraday Delta hedging strategies and offering substantially faster computation than Fourier-based benchmarks.
0 citationsRead paper