Anthony Man–Cho So

Variance-Reduced Stochastic Quasi-Newton Methods for Decentralized Learning: Part II

2022 · arXiv (Cornell University)

In Part I of this work, we have proposed a general framework of decentralized stochastic quasi-Newton methods, which converge linearly to the optimal solution under the assumption that the local Hessian inverse approximations have bounded …

On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions

2021 · arXiv (Cornell University)

We report a practical finite-time algorithmic scheme to compute approximately stationary points for nonconvex nonsmooth Lipschitz functions. In particular, we are interested in two kinds of approximate stationarity notions for nonconvex nonsmooth problems, i.e., Goldstein …