Research map / Optimization / Nonconvex and smooth optimization
Dual-Free Stochastic Decentralized Optimization with Variance Reduction
Hadrien Hendrikx, Francis R. Bach, Laurent Massoulié
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 DVR instead of EXTRA | Decentralized logistic regression · RCV1 | computation complexity | Improved |
| Use DVR instead of EXTRA | Decentralized logistic regression · RCV1, τ = 250 | simulated runtime | Improved |
| Use DVR instead of EXTRA | Decentralized logistic regression · RCV1, τ ≈ 1000 | simulated runtime | No clear effect |
| Use Catalyst-accelerated DVR instead of DVR | DVR · RCV1 | simulated runtime | Improved |
| Use Catalyst-accelerated DVR instead of other evaluated methods | Decentralized logistic regression · RCV1 | simulated runtime | Improved |
| Use Catalyst-accelerated EXTRA instead of EXTRA | EXTRA · RCV1, higher regularization | simulated runtime | Hurt |
| Use GT-SAGA instead of the other plotted methods | Decentralized logistic regression · RCV1 | simulated runtime | Hurt |
Closest papers by meaning
- Decentralized Non-convex Stochastic Optimization with Heterogeneous Variance (AAAI 2026 · similarity 0.92)
- Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization (JMLR 2022 · similarity 0.90)
- Enhancing Parallelism in Decentralized Stochastic Convex Optimization (ICML 2025 · similarity 0.89)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.89)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 2024 · similarity 0.89)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · 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.
