New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Implement SPSA #82

Open

HEmile opened this issue Sep 17, 2020 · 0 comments

Owner

HEmile commented Sep 17, 2020

Simultaneous perturbation stochastic approximation (SPSA) is a finite-differences like method. It fits well in the framework:

Perturb the parameters of the probability distribution
Sample from each
Compute importance weights for the sample (the perturbed distribution is no longer the distribution to optimize!)
Use multiplicative estimator: Inverse of weight times the parameter, and negated for the negative component.

This is similar to how measure-valued derivatives would be implemented.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment