On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond
Authors: Xiaotong Yuan, Ping Li
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our work is focused on providing deeper theoretical understandings of Fed Prox and its stochastic variants under milder conditions. 3. If you ran experiments... [N/A] Our work is focused on providing deeper theoretical understandings of Fed Prox and its stochastic variants under milder conditions. |
| Researcher Affiliation | Collaboration | Xiao-Tong Yuan Nanjing Univ. of Information Sci. & Tech. 219 Ningliu Rd, Nanjing, China xtyuan1980@gmail.com Ping Li Linked In Ads 700 Bellevue Way NE, Bellevue, WA, USA pinli@linkedin.com |
| Pseudocode | Yes | Algorithm 1: Fed MSPP: Federated Minibatch Stochastic Proximal Point |
| Open Source Code | No | 4. If you are using existing assets (e.g., code, data, models) or curating/releasing new assets... [N/A] We did not use any of such assets in this work. |
| Open Datasets | No | 3. If you ran experiments... [N/A] Our work is focused on providing deeper theoretical understandings of Fed Prox and its stochastic variants under milder conditions. |
| Dataset Splits | No | 3. If you ran experiments... [N/A] Our work is focused on providing deeper theoretical understandings of Fed Prox and its stochastic variants under milder conditions. |
| Hardware Specification | No | 3. If you ran experiments... [N/A] Our work is focused on providing deeper theoretical understandings of Fed Prox and its stochastic variants under milder conditions. |
| Software Dependencies | No | The paper does not describe experimental implementations and therefore does not list specific software dependencies with version numbers. |
| Experiment Setup | No | 3. If you ran experiments... [N/A] Our work is focused on providing deeper theoretical understandings of Fed Prox and its stochastic variants under milder conditions. |