Unified Optimality Conditions for Stochastic Optimal Control in the Rough Path and Itô Frameworks
Abstract
Stochastic differential equations (SDEs) can be studied via Itô calculus and rough path theory. For stochastic optimal control, these two frameworks give distinct Pontryagin Maximum Principle (PMP) optimality conditions with forward-backward SDEs (FBSDEs) or rough differential equations. We show that the adjoint equations of the Itô and rough PMPs are connected via the conditional expectation ptItô=𝔼[ptrough | ℱt], where ℱt represents information available at time t. First, we derive a rough stochastic PMP for problems with adapted controls that does not use FBSDEs. Its proof extends the rough stochastic PMP over deterministic controls by considering stochastic needle variations. Second, we derive a unified PMP connecting the Itô and rough PMPs, using Itô-Stratonovich conversion formulas and duality identities between the forward tangent and backward adjoint SDEs. As a first application, we rederive the adjoint matching method for fine-tuning generative models. As a second application, we propose an indirect shooting method for a class of feedback problems. Overall, these results give a new conditional bridge connecting two popular frameworks for stochastic optimal control.
Related
- On quantitative sufficient second-order optimality conditions for elliptic optimal control problems
- Necessary and sufficient conditions for optimal control of coupled forward-backward stochastic control systems driven by G-Brownian motion
- Underdamped Stochastic Optimal Transport with Landauer boundary conditions: machine learning and analytical solution
- Optimality Conditions and Solution Set Characterisations of Convex Minimal Time Optimisation Problems
- Movable Antenna Enabled Anti-Jamming: From Local Optimality Guaranteed Design to a Unified Antenna Position Optimization Framework
BibTeX
@misc{lew2026unified,
title = {{Unified Optimality Conditions for Stochastic Optimal Control in the Rough Path and Itô Frameworks}},
author = {Thomas Lew},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38395},
eprint = {2609.38395},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38395},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Unified Optimality Conditions for Stochastic Optimal Control in the Rough Path and Itô Frameworks
AU - Thomas Lew
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38395
UR - https://arxiv.org/abs/2609.38395
AB - Stochastic differential equations (SDEs) can be studied via Itô calculus and rough path theory. For stochastic optimal control, these two frameworks give distinct Pontryagin Maximum Principle (PMP) optimality conditions with forward-backward SDEs (FBSDEs) or rough differential equations. We show that the adjoint equations of the Itô and rough PMPs are connected via the conditional expectation p_t^Itô=𝔼[p_t^rough | ℱ_t], where ℱ_t represents information available at time t. First, we derive a rough stochastic PMP for problems with adapted controls that does not use FBSDEs. Its proof extends the rough stochastic PMP over deterministic controls by considering stochastic needle variations. Second, we derive a unified PMP connecting the Itô and rough PMPs, using Itô-Stratonovich conversion formulas and duality identities between the forward tangent and backward adjoint SDEs. As a first application, we rederive the adjoint matching method for fine-tuning generative models. As a second application, we propose an indirect shooting method for a class of feedback problems. Overall, these results give a new conditional bridge connecting two popular frameworks for stochastic optimal control.
ER -