Search Results for author:
Found 1 papers, 0 papers with code
Dual Stochastic Natural Gradient Descent and convergence of interior half-space gradient approximations
Here, we propose a stochastic optimization method for MLR based on manifold optimization concepts which (i) has per-iteration computational complexity is linear in the number of parameters and (ii) can be proven to converge.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
