In this paper, we present the first stepsize schedule for Newton method resulting in fast
global and local convergence guarantees. In particular, we a) prove an $\mathcal O\left …

There is a growing interest in the distributed optimization framework that goes under the
name of Federated Learning (FL). In particular, much attention is being turned to FL …

Though quasi-Newton methods have been extensively studied in the literature, they either
suffer from local convergence or use a series of line searches for global convergence which …

Federated learning is a distributed learning framework that allows a set of clients to
collaboratively train a model under the orchestration of a central server, without sharing raw …

In this paper, we propose Cubic Regularized Quasi-Newton Methods for (strongly)
starconvex and Accelerated Cubic Regularized Quasi-Newton for convex optimization. The …

Federated learning is a distributed learning framework that allows a set of clients to
collaboratively train a model under the orchestration of a central server, without sharing raw …

Methods with preconditioned updates show up well in badly scaled and/or ill-conditioned
convex optimization problems. However, theoretical analysis of these methods in distributed …

In the recent paper FLECS (Agafonov et al, FLECS: A Federated Learning Second-Order
Framework via Compression and Sketching), the second-order framework FLECS was …

Federated learning is a machine learning approach where multiple devices collaboratively
learn with the help of a parameter server by sharing only their local updates. While gradient …

The Hessian matrix conveys important information about the curvature, spectrum and partial
derivatives of a function, and is required in a variety of tasks. However, computing the exact …