6 papers · 1 filter
Spherical-Design Oracles for Zeroth-Order Optimisation: Deterministic, Variance-Free Gradient Estimation
Amir Ali Farzin, Yuen-Man Pun, Philipp Braun +1
In this work, we develop a zeroth-order (ZO) method that estimates the gradient with minimal bias and variance. Instead of the random directions often used in the ZO literature, we…
Semi-Explicit Solutions to the Prying-Pedestrian Surveillance-Evasion Differential Game and Extensions to Two Pursuers
Philipp Braun, Daniel Coutinho, Timothy L. Molloy +1
In [1], the authors recently proposed and solved a surveillance-evasion differential game in which an agile pursuer (the prying pedestrian) seeks to remain within a given surveilla…
From open-loop representations to closed-loop feedback implementations in differential games: A numerical case study
Philipp Braun, Timothy L. Molloy, Gal Barkai +1
Solutions to pursuit-evasion and surveillance-evasion differential games are typically computed and expressed using open-loop representations, with the synthesis of feedback strate…
From Cursed to Competitive: Closing the ZO-FO Gap via Input-to-State Stability
Amir Ali Farzin, Philipp Braun, Iman Shames
While it is generally understood that zeroth-order (ZO) algorithms have an extra dependency on their number of iterations for any choice of parameters, compared to their first-orde…
On the Stability Connection Between Discrete-Time Algorithms and Their Resolution ODEs: Applications to Min-Max Optimisation
Amir Ali Farzin, Yuen-Man Pun, Philipp Braun +1
This work establishes a rigorous connection between stability properties of discrete-time algorithms (DTAs) and corresponding continuous-time dynamical systems derived through $ O(…
Solving the Offline and Online Min-Max Problem of Non-smooth Submodular-Concave Functions: A Zeroth-Order Approach
Amir Ali Farzin, Yuen-Man Pun, Philipp Braun +2
We consider max-min and min-max problems with objective functions that are possibly non-smooth, submodular with respect to the minimiser and concave with respect to the maximiser.…