3 papers
cs.LG2024
Automatic Gradient Estimation for Calibrating Crowd Models with Discrete Decision Making
Philipp Andelfinger, Justin N. Kreikemeyer
Recently proposed gradient estimators enable gradient descent over stochastic programs with discrete jumps in the response surface, which are not covered by automatic differentiati…
cs.LG2024
Towards Learning Stochastic Population Models by Gradient Descent
Justin N. Kreikemeyer, Philipp Andelfinger, Adelinde M. Uhrmacher
Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters but also a suit…
cs.LG2023
Smoothing Methods for Automatic Differentiation Across Conditional Branches
Justin N. Kreikemeyer, Philipp Andelfinger
Programs involving discontinuities introduced by control flow constructs such as conditional branches pose challenges to mathematical optimization methods that assume a degree of s…