Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.16117 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917903614345216 |
|---|---|
| author | Li, Yipeng Lyu, Xinchen Liu, Zhenyu |
| author_facet | Li, Yipeng Lyu, Xinchen Liu, Zhenyu |
| contents | We aim to provide a unified convergence analysis for permutation-based Stochastic Gradient Descent (SGD), where data examples are permuted before each epoch. By examining the relations among permutations, we categorize existing permutation-based SGD algorithms into four categories: Arbitrary Permutations, Independent Permutations (including Random Reshuffling), One Permutation (including Incremental Gradient, Shuffle One and Nice Permutation) and Dependent Permutations (including GraBs Lu et al., 2022; Cooper et al., 2023). Existing unified analyses failed to encompass the Dependent Permutations category due to the inter-epoch dependencies in its permutations. In this work, we propose a general assumption that captures the inter-epoch permutation dependencies. Using the general assumption, we develop a unified framework for permutation-based SGD with arbitrary permutations of examples, incorporating all the aforementioned representative algorithms. Furthermore, we adapt our framework on example ordering in SGD for client ordering in Federated Learning (FL). Specifically, we develop a unified framework for regularized-participation FL with arbitrary permutations of clients. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16117 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond Li, Yipeng Lyu, Xinchen Liu, Zhenyu Machine Learning We aim to provide a unified convergence analysis for permutation-based Stochastic Gradient Descent (SGD), where data examples are permuted before each epoch. By examining the relations among permutations, we categorize existing permutation-based SGD algorithms into four categories: Arbitrary Permutations, Independent Permutations (including Random Reshuffling), One Permutation (including Incremental Gradient, Shuffle One and Nice Permutation) and Dependent Permutations (including GraBs Lu et al., 2022; Cooper et al., 2023). Existing unified analyses failed to encompass the Dependent Permutations category due to the inter-epoch dependencies in its permutations. In this work, we propose a general assumption that captures the inter-epoch permutation dependencies. Using the general assumption, we develop a unified framework for permutation-based SGD with arbitrary permutations of examples, incorporating all the aforementioned representative algorithms. Furthermore, we adapt our framework on example ordering in SGD for client ordering in Federated Learning (FL). Specifically, we develop a unified framework for regularized-participation FL with arbitrary permutations of clients. |
| title | A Unified Analysis of Stochastic Gradient Descent with Arbitrary Data Permutations and Beyond |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.16117 |