34 citations · 93 across the 18 of their papers we have counts for
20 papers
Convergence Analysis of Noisy Distributed Gradient Descent for Non-convex Optimization -- Saddle Point Escape
Lei Qin, Michael Cantoni, Ye Pu
This paper studies noisy distributed gradient descent (\textbf{NDGD}) for smooth non-convex finite-sum optimization over networks. Random perturbations enable saddle-point escape w…
On receding-horizon approximation in time-varying optimal control
Jintao Sun, Michael Cantoni
The closed-loop stability and infinite-horizon performance of receding-horizon approximations are studied for non-stationary linear-quadratic regulator (LQR) problems. The approach…
On Riccati contraction in time-varying linear-quadratic control
Jintao Sun, Michael Cantoni
Contraction properties of the Riccati operator are studied within the context of non-stationary linear-quadratic optimal control. A lifting approach is used to obtain a bound on th…
Second-order Properties of Noisy Distributed Gradient Descent
Lei Qin, Michael Cantoni, Ye Pu
We study a fixed step-size noisy distributed gradient descent algorithm for solving optimization problems in which the objective is a finite sum of smooth but possibly non-convex f…
Explicit Time-Optimal Speed Profiles for Planar Paths with Monotone Curvature
Daniel Selvaratnam, Michael Cantoni, Chris Manzie
Minimum-time speed profiles are constructed for planar paths with smooth strictly-monotonic signed curvature, subject to constraints on velocity, normal acceleration and tangential…
MITL Verification Under Timing Uncertainty
Daniel Selvaratnam, Michael Cantoni, J. M. Davoren +1
A Metric Interval Temporal Logic (MITL) verification algorithm is presented. It verifies continuous-time signals without relying on high frequency sampling. Instead, it is assumed…