A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909059778609152 |
|---|---|
| author | Tyurin, Alexander Richtárik, Peter |
| author_facet | Tyurin, Alexander Richtárik, Peter |
| contents | We present a new method that includes three key components of distributed optimization and federated learning: variance reduction of stochastic gradients, partial participation, and compressed communication. We prove that the new method has optimal oracle complexity and state-of-the-art communication complexity in the partial participation setting. Regardless of the communication compression feature, our method successfully combines variance reduction and partial participation: we get the optimal oracle complexity, never need the participation of all nodes, and do not require the bounded gradients (dissimilarity) assumption. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_15580 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting Tyurin, Alexander Richtárik, Peter Machine Learning Optimization and Control We present a new method that includes three key components of distributed optimization and federated learning: variance reduction of stochastic gradients, partial participation, and compressed communication. We prove that the new method has optimal oracle complexity and state-of-the-art communication complexity in the partial participation setting. Regardless of the communication compression feature, our method successfully combines variance reduction and partial participation: we get the optimal oracle complexity, never need the participation of all nodes, and do not require the bounded gradients (dissimilarity) assumption. |
| title | A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2205.15580 |