dorsal/arxiv
View SchemaAccelerated Methods with Complexity Separation Under Data Similarity for Federated Learning Problems
| Authors | Dmitry Bylinkin, Sergey Skorik, Dmitriy Bystrov, Leonid Berezin, Aram Avetisyan, Aleksandr Beznosikov |
|---|---|
| Categories | |
| ArXiv ID | 2601.08614vv1 |
| URL | https://arxiv.org/abs/2601.08614 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Heterogeneity within data distribution poses a challenge in many modern federated learning tasks. We formalize it as an optimization problem involving a computationally heavy composite under data similarity. By employing different sets of assumptions, we present several approaches to develop communication-efficient methods. An optimal algorithm is proposed for the convex case. The constructed theory is validated through a series of experiments across various problems.
{
"annotation_id": "f6fe1831-4cc5-4cd9-8803-f0d280ff683a",
"date_created": "2026-02-17T05:53:16.250000Z",
"date_modified": "2026-02-17T05:53:16.250000Z",
"file_hash": "345974673aba6e53eb61de66fc3d3db35a5360f9d36524f1844a86aee89a6473",
"private": false,
"record": {
"abstract": "Heterogeneity within data distribution poses a challenge in many modern federated learning tasks. We formalize it as an optimization problem involving a computationally heavy composite under data similarity. By employing different sets of assumptions, we present several approaches to develop communication-efficient methods. An optimal algorithm is proposed for the convex case. The constructed theory is validated through a series of experiments across various problems.",
"arxiv_id": "2601.08614",
"authors": [
"Dmitry Bylinkin",
"Sergey Skorik",
"Dmitriy Bystrov",
"Leonid Berezin",
"Aram Avetisyan",
"Aleksandr Beznosikov"
],
"categories": [
"math.OC",
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Accelerated Methods with Complexity Separation Under Data Similarity for Federated Learning Problems",
"url": "https://arxiv.org/abs/2601.08614",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "47de834f-ffc4-4157-82fc-29de5c478761",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}