Riemannian Stochastic Approximation for Minimizing Tame Nonsmooth Objective Functions.

Johannes Aspman Vyacheslav Kungurtsev Reza Roohi Seraji

Published in: CoRR (2023)

Keyphrases

stochastic approximation
convex functions
objective function
monte carlo
linear program
cost function
policy iteration
temporal difference learning
reinforcement learning
mathematical programming
optimal solution
linear programming
image segmentation
multi agent
primal dual