Reflected Optimal Stopping with a Max-Type Payoff: Measure-Valued Stopping Gains and Killed Resolvent Representation
arXiv:2607.09987
2026
Regularization
2 ideas extracted · analyzed Aug 30, 2026
What the math gives to ML
The paper provides a precise way to handle nonsmooth max-type objectives in diffusion and obstacle problems: the stopping gain is not an ordinary function, because the kink contributes a singular measure concentrated on the switching surface. This is transferable to neural modules involving maxout, max pooling, hard mixture-of-experts routing, and obstacle-style value networks, where treating the max as twice differentiable gives incorrect curvature or PDE residuals. The most actionable adaptations are a kink-aware covariance regularizer and a killed-resolvent residual for neural obstacle solvers.
Ideas from this paper
Unverified
2026
Use the paper's singular stopping-gain term to explicitly measure how much learned feature covariance crosses a max or routing boundary. Penalize excessive covariance in the normal direction to the switching surface, rather than pretending that the max operation has an ordinary Hessian.
Useful6/10
Difficulty5/10
Novelty7/10
Unverified
2026
Train a value network for stopping or intervention decisions using a killed-resolvent identity rather than an unrestricted diffusion residual. Simulating only until the process exits the continuation region makes the learning target local to the relevant decision domain and correctly handles nonsmooth max rewards.
Useful5/10
Difficulty6/10
Novelty8/10