Research map / Optimization / Distributed and compressed
On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use exponentially increasing batch sizes in parallel SGD | Parallel SGD under the P-L condition · Stochastic non-convex optimization under P-L condition | communication rounds: O(T) -> O(log(T)) | Helped |
| Use exponentially increasing batch sizes in parallel SGD | Parallel SGD under the P-L condition · Stochastic non-convex optimization under P-L condition | convergence rate: O(1/(NT)) | Helped |
| Wrap CR-PSGD in a proximal-point outer loop | CR-PSGD · General stochastic non-convex optimization | communication rounds: O(T) -> O(sqrt(TN)log(T/N)) | Helped |
| Wrap CR-PSGD in a proximal-point outer loop | CR-PSGD · General stochastic non-convex optimization | convergence rate: O(1/sqrt(NT)) | Helped |
Closest papers by meaning
- STL-SGD: Speeding Up Local SGD with Stagewise Communication Period (AAAI 2021 · similarity 0.91)
- Enhancing Parallelism in Decentralized Stochastic Convex Optimization (ICML 2025 · similarity 0.89)
- Tight Time Complexities in Parallel Stochastic Optimization with Arbitrary Computation Dynamics (ICLR 2025 · similarity 0.89)
- Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity (NeurIPS 2024 · similarity 0.88)
- Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity (NeurIPS 2024 · similarity 0.88)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.