12 citations · 18 across the 11 of their papers we have counts for
4 papers · 1 filter
Curvature Aligned Simplex Gradient: Principled Sample Set Construction For Numerical Differentiation
Daniel Lengyel, Panos Parpas, Nikolas Kantas +1
The simplex gradient, a popular numerical differentiation method due to its flexibility, lacks a principled method by which to construct the sample set, specifically the location o…
Simba: A Scalable Bilevel Preconditioned Gradient Method for Fast Evasion of Flat Areas and Saddle Points
Nick Tsipinakis, Panos Parpas
The convergence behaviour of first-order methods can be severely slowed down when applied to high-dimensional non-convex functions due to the presence of saddle points. If, additio…
Adaptive Multilevel Newton: A Quadratically Convergent Optimization Method
Nick Tsipinakis, Panagiotis Tigkas, Panos Parpas
Newton's method may exhibit slower convergence than vanilla Gradient Descent in its initial phase on strongly convex problems. Classical Newton-type multilevel methods mitigate thi…
Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds
Anastasia Borovykh, Nikolas Kantas, Panos Parpas +1
The privacy preserving properties of Langevin dynamics with additive isotropic noise have been extensively studied. However, the isotropic noise assumption is very restrictive: (a)…