Research map / Optimization / Distributed and compressed
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?
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 polynomially growing gradient delays (d_n = O(n^q)) with step size alpha_n ∝ 1/(n log n log log n) instead of bounded delays | DASGD on stochastic variationally coherent problems · theoretical convergence analysis | almost sure convergence to global minimizer | No clear effect |
| Use linearly growing delays with step size 1/(n log n) instead of bounded delays (ablation) | DAGD on Rosenbrock (d=101) with synchronous baseline comparison · Rosenbrock function d=101 | value convergence in simulation | No clear effect |
| Use ergodic averaging of iterates (weighted average) instead of last iterate X_n (ablation) | DASGD on non-convex Rosenbrock function · Rosenbrock function d=101 | value convergence | Hurt |
Closest papers by meaning
- Delay-Adaptive Distributed Stochastic Optimization (AAAI 2020 · similarity 0.95)
- Asynchronous Stochastic Optimization Robust to Arbitrary Delays (NeurIPS 2021 · similarity 0.91)
- Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity (NeurIPS 2026 · similarity 0.91)
- Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching (ICML 2025 · similarity 0.89)
- Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity (ICML 2025 · similarity 0.89)
- Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness (NeurIPS 2024 · similarity 0.89)
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.