16 papers
This paper introduces and proves the convergence of a Martingale Sinkhorn algorithm in arbitrary dimensions for solving the martingale Benamou–Brenier optimal transport problem, extending the theory to marginals with finite moments of order without requiring compact support.
This paper introduces "stochastic attention," a training-free method that interprets attention as gradient descent on a Hopfield energy function and utilizes Langevin dynamics to enable a single temperature-controlled mechanism for both exact retrieval and diverse, novel generation without requiring learned score networks or architectural changes.
This paper proposes the Time-series Neural Causal Model VAE (TNCM-VAE), a novel framework that integrates variational autoencoders with structural causal models to generate synthetic financial time series that preserve both temporal dependencies and causal relationships, thereby enabling robust counterfactual analysis and risk assessment.
This paper introduces Augmented Time Series Causal Models (ATSCM), a novel framework that integrates neural causal discovery with counterfactual reasoning to dynamically model complex, time-varying causal relationships in energy markets and enable interpretable scenario analysis for electricity price formation.
This paper solves Merton's portfolio optimization problem in a multivariate fake stationary affine Volterra setting by employing a martingale optimality principle and a Riccati backward stochastic differential equation to derive semi-closed form optimal strategies, overcoming the challenges posed by non-Markovian and non-semimartingale dynamics.
This paper introduces a machine learning framework that utilizes a directed bipartite graph to model time-ordered predictive linkages between U.S. and Chinese equity markets, revealing a significant directional asymmetry where U.S. returns strongly predict Chinese intraday performance while the reverse effect is limited.
This paper proposes a model-independent framework that utilizes perturbed optimal transport and Fisher information linearization to rapidly generate accurate SPX and VIX risk scenarios and hedging strategies without requiring full recalibration after market shocks.
This paper introduces a risk-aware evaluation framework for Large Language Models in financial services, featuring a domain-specific taxonomy, an automated multi-round red-teaming pipeline, and a Risk-Adjusted Harm Score (RAHS) metric to better capture and quantify severe, operationally actionable security failures that traditional domain-agnostic benchmarks miss.
This paper introduces an uncertainty-aware deep hedging framework that utilizes a deep ensemble of LSTMs to quantify model confidence, enabling a CVaR-optimized blending strategy with the Black-Scholes delta that significantly outperforms both classical and theoretically optimal hedging approaches, particularly when model agreement is high.
This paper presents a neural network framework for multi-period risk-reward stochastic control with discontinuous, constrained policies, proving that the empirical optimum of the parametrized objective converges in probability to the true optimal value as network capacity and sample size increase, while numerical experiments validate the method's accuracy and out-of-sample robustness.
Using artificial market simulations, this study demonstrates that arbitrage trading between leveraged ETFs and futures acts as a critical liquidity bridge during market crashes, supplying depth and tightness from the stable market to the distressed one to mitigate price declines.
This paper introduces a novel class of single- and multi-level Fourier-RQMC algorithms that leverage frequency-domain integration and randomized quasi-Monte Carlo sampling to achieve superior accuracy and computational efficiency in estimating multivariate shortfall risk and optimal capital allocations compared to traditional Monte Carlo methods.
This paper introduces a differential machine learning framework for pricing 0DTE options under stochastic volatility and jumps, which utilizes a specialized network architecture and a three-stage training procedure to simultaneously compute accurate prices and Greeks while significantly outperforming traditional Fourier-based benchmarks in speed and stability.
This paper introduces two shortfall-aware reinforcement learning frameworks, RLOP and QLBS, which outperform traditional parametric models in reducing tail risk and hedging shortfalls for SPY and XOP options, thereby offering a more robust approach to autonomous derivatives risk management.
This paper proposes an enhanced indexation framework that treats index options as artificial assets through defined trading rules, demonstrating via S&P 500 data (2017–2025) and second-order stochastic dominance that integrating these option strategies significantly improves out-of-sample portfolio performance.
This paper analyzes an optimal stopping problem with a discontinuous reward function motivated by variable annuity pricing, establishing conditions under which surrender occurs only at maturity and deriving new analytical representations for the value function and surrender region based on fee and surrender charge structures.