Stochastic Sample Approximations of (Local) Moduli of Continuity
This work addresses robustness and fairness issues in neural networks for applications like closed-loop systems, but it appears incremental as it builds on existing connections with generalized derivatives.
The paper tackles the problem of evaluating neural network robustness and fairness in closed-loop models by introducing a non-uniform stochastic sample approximation for moduli of local continuity, leveraging a connection with generalized derivatives.
Modulus of local continuity is used to evaluate the robustness of neural networks and fairness of their repeated uses in closed-loop models. Here, we revisit a connection between generalized derivatives and moduli of local continuity, and present a non-uniform stochastic sample approximation for moduli of local continuity. This is of importance in studying robustness of neural networks and fairness of their repeated uses.