Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates.

Alp Yurtsever Alex Gu Suvrit Sra

Published in: NeurIPS (2021)

Keyphrases

learning rate
operator splitting
gaussian kernels
learning algorithm
convergence rate
convergence speed
convex optimization
partial differential equations
uniform convergence
covering numbers
objective function
weight vector