Research map / Optimization / Nonconvex and smooth optimization
Lock-Free Optimization for Non-Convex Problems
Shen-Yi Zhao, Gong-Duo Zhang, Wu-Jun Li
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 lock-free AsySVRG instead of lock-free Hogwild! | Hogwild! and AsySVRG · Neural-network experiments on connect-4 and MNIST | training loss versus CPU time | Improved |
| Increase the thread count | Hogwild! and AsySVRG · connect-4 and MNIST | training speed | Mixed |
| Increase Hogwild! from 1 to 4 threads | Hogwild! · connect-4 | training speed | Hurt |
Closest papers by meaning
- Fast Asynchronous Parallel Stochastic Gradient Descent: A Lock-Free Approach with Convergence Guarantee (AAAI 2016 · similarity 0.90)
- On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization (ICML 2019 · similarity 0.87)
- Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness (ICML 2021 · similarity 0.87)
- Gradient correlation is a key ingredient to accelerate SGD with momentum (ICLR 2025 · similarity 0.86)
- Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions (NeurIPS 2025 · similarity 0.86)
- Random Scaling and Momentum for Non-smooth Non-convex Optimization (ICML 2024 · similarity 0.86)
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.
