A sensitivity analysis reduces nonlinear Kolmogorov PDEs (nonlinearity from ε-neighborhood max over drifts/diffusions) to a linear PDE plus ε times a second linear PDE, enabling efficient high-dimensional Monte Carlo approximation with error bounds.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2024 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.
citing papers explorer
-
Numerical method for nonlinear Kolmogorov PDEs via sensitivity analysis
A sensitivity analysis reduces nonlinear Kolmogorov PDEs (nonlinearity from ε-neighborhood max over drifts/diffusions) to a linear PDE plus ε times a second linear PDE, enabling efficient high-dimensional Monte Carlo approximation with error bounds.
-
Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.