7 citations · 8 across the 3 of their papers we have counts for
Showing math.OCShow all
2 papers · 1 filter
math.OC2024★ 1 cited
A Pseudo-Gradient Approach for Model-free Markov Chain Optimization
Nanne A. Dieleman, Joost Berkhout, Bernd Heidergott
We develop a first-order (pseudo-)gradient approach for optimizing functions over the stationary distribution of discrete-time Markov chains (DTMC). We give insights into why solvi…
math.OC2016
Differentiation via Logarithmic Expansions
Michael C. Fu, Bernd Heidergott, Haralambie Leahu +1
In this note, we introduce a new finite difference approximation called the Black-Box Logarithmic Expansion Numerical Derivative (BLEND) algorithm, which is based on a formal logar…