5 papers
Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking
Qian Qi, Jiangyun Tang, Jim Lee +2
Robust invisible watermarks are widely used to support copyright protection, content provenance, and accountability by embedding hidden signals designed to survive common post-proc…
Robust Control with Gradient Uncertainty
Qian Qi
We introduce a novel extension to robust control theory that explicitly addresses uncertainty in the value function's gradient, a form of uncertainty endemic to applications like r…
Propagation of Chaos for Singular Interactions via Regular Drivers
Qian Qi
We introduce a framework to prove propagation of chaos for interacting particle systems with singular, density-dependent interactions, a classical challenge in mean-field theory. O…
Universal Approximation Theorem for Deep Q-Learning via FBSDE System
Qian Qi
The approximation capabilities of Deep Q-Networks (DQNs) are commonly justified by general Universal Approximation Theorems (UATs) that do not leverage the intrinsic structural pro…
Universal Approximation Theorem of Deep Q-Networks
Qian Qi
We establish a continuous-time framework for analyzing Deep Q-Networks (DQNs) via stochastic control and Forward-Backward Stochastic Differential Equations (FBSDEs). Considering a…