8 citations · 11 across the 4 of their papers we have counts for
3 papers · 1 filter
Zeroth order optimization with orthogonal random directions
David Kozak, Cesare Molinari, Lorenzo Rosasco +2
We propose and analyze a randomized zeroth-order approach based on approximating the exact gradient byfinite differences computed in a set of orthogonal random directions that chan…
A stochastic subspace approach to gradient-free optimization in high dimensions
David Kozak, Stephen Becker, Alireza Doostan +1
We present a stochastic descent algorithm for unconstrained optimization that is particularly efficient when the objective function is slow to evaluate and gradients are not easily…
Stochastic Subspace Descent
David Kozak, Stephen Becker, Alireza Doostan +1
We present two stochastic descent algorithms that apply to unconstrained optimization and are particularly efficient when the objective function is slow to evaluate and gradients a…