Introduces feedback-type ambiguity sets for robust Bayesian drift uncertainty in continuous-time portfolio optimization, yielding a modified HJBI equation and classical solution existence for exponential utility via verification theorem.
arXiv preprint arXiv:2411.02549 , year=
5 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
5
Pith papers citing it
1
external citations · external index
representative citing papers
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
SV-DRO evolves parameter particles via task-optimality-gap Stein gradients inside DRO-MPC, yielding up to 3× higher success on contact-rich manipulation under parametric uncertainty.
AGM adds a gradient-based masking loss during fine-tuning to suppress reliance on spurious tokens, achieving competitive zero-shot transfer on sentiment tasks while providing token-level interpretability.
DRO regularizers are worst-case sensitivities of expected cost, supplying a robustness measure that guides uncertainty-set selection and traces performance-robustness frontiers.
citing papers explorer
-
Robust Bayesian Portfolio Optimization with Discrepancy-based Posterior Ambiguity
Introduces feedback-type ambiguity sets for robust Bayesian drift uncertainty in continuous-time portfolio optimization, yielding a modified HJBI equation and classical solution existence for exponential utility via verification theorem.
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation
SV-DRO evolves parameter particles via task-optimality-gap Stein gradients inside DRO-MPC, yielding up to 3× higher success on contact-rich manipulation under parametric uncertainty.
-
Attribution-Guided Masking for Robust Cross-Domain Sentiment Classification
AGM adds a gradient-based masking loss during fine-tuning to suppress reliance on spurious tokens, achieving competitive zero-shot transfer on sentiment tasks while providing token-level interpretability.
-
Robustness Measures in Distributionally Robust Optimization
DRO regularizers are worst-case sensitivities of expected cost, supplying a robustness measure that guides uncertainty-set selection and traces performance-robustness frontiers.