Pith. sign in

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

arxiv 2210.09626 v1 pith:JKOOMLK5 submitted 2022-10-18 cs.LG math.OC

classification cs.LGmath.OC
keywords flecscompressiongradientcompresseddifferencesfederatedframeworklearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees

    math.OC 2025-08 conditional novelty 5.0 of 10

    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.

Pith tools