2 citations · 3 across the 3 of their papers we have counts for
5 papers
Probabilistic Verification of ReLU Neural Networks via Characteristic Functions
Joshua Pilipovsky, Vignesh Sivaramakrishnan, Meeko M. K. Oishi +1
Verifying the input-output relationships of a neural network so as to achieve some desired performance specification is a difficult, yet important, problem due to the growing ubiqu…
Distribution Steering for Discrete-Time Linear Systems with General Disturbances using Characteristic Functions
Vignesh Sivaramakrishnan, Joshua Pilipovsky, Meeko M. K. Oishi +1
We propose to solve a constrained distribution steering problem, i.e., steering a stochastic linear system from an initial distribution to some final, desired distribution subject…
Convexified Open-Loop Stochastic Optimal Control for Linear Non-Gaussian Systems
Vignesh Sivaramakrishnan, Abraham P. Vinod, Meeko M. K. Oishi
We consider stochastic optimal control of linear dynamical systems with additive non-Gaussian disturbance. We propose a novel, sampling-free approach, based on Fourier transformati…
Fast, Convexified Stochastic Optimal Open-Loop Control For Linear Systems Using Empirical Characteristic Functions
Vignesh Sivaramakrishnan, Meeko M. K. Oishi
We consider the problem of stochastic optimal control in the presence of an unknown disturbance. We characterize the disturbance via empirical characteristic functions, and employ…
Approximate Stochastic Reachability for High Dimensional Systems
Adam J. Thorpe, Vignesh Sivaramakrishnan, Meeko M. K. Oishi
We present a method to compute the stochastic reachability safety probabilities for high-dimensional stochastic dynamical systems. Our approach takes advantage of a nonparametric l…