REVIEW 1 cited by
FLECS-CGD: A Federated Learning Second-Order Framework via Compression and Sketching with Compressed Gradient Differences
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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 proposed for the Federated Learning problem. This method utilize compression of sketched Hessians to make communication costs low. However, the main bottleneck of FLECS is gradient communication without compression. In this paper, we propose the modification of FLECS with compressed gradient differences, which we call FLECS-CGD (FLECS with Compressed Gradient Differences) and make it applicable for stochastic optimization. Convergence guarantees are provided in strongly convex and nonconvex cases. Experiments show the practical benefit of proposed approach.
Forward citations
Cited by 1 Pith paper
-
Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
An explicit stepsize schedule for quasi-Newton updates achieves O(1/k) global convergence on convex functions, and O(1/k^2) when Hessian approximation error is controlled.
Discussion (0). Continue with ORCID to comment.