Research map / Optimization / Nonconvex and smooth optimization
The Sound of APALM Clapping: Faster Nonsmooth Nonconvex Optimization with Stochastic Asynchronous PALM
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 |
|---|---|---|---|
| Asynchronous parallel execution with more workers (up to 16 threads) | SAPALM · Sparse PCA, n=2000 | speedup over 1 thread at 16 iterations: up to 13.376x (d=10), 14.5322x (d=20), 14.743x (d=100) | Helped |
| Asynchronous parallel execution with stochastic gradient noise / more workers reduces wall-clock time to fixed iterations | SAPALM · Sparse PCA d=10 | wall-clock time for 16 iterations: 65.9972 s (1 thread) to 4.934 s (16 threads) | Helped |
| Asynchronous updates with more workers vs. iteration-wise objective | SAPALM · Sparse PCA and Firm Thresholding PCA objective per iteration | objective value vs iterations | No clear effect |
| Increasing thread count beyond 8 on large dimension problem (write conflicts / cache contention) | SAPALM · Sparse PCA, small d | speedup efficiency: near-linear for small d, deviations attributed to cache coherency and L3 contention; speedup reduced for d=10 relative t | Mixed |
Closest papers by meaning
- Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization (NeurIPS 2016 · similarity 0.90)
- Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization (NeurIPS 2017 · similarity 0.90)
- Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations (NeurIPS 2024 · similarity 0.89)
- Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching (ICML 2025 · similarity 0.88)
- Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints (ICML 2025 · similarity 0.87)
- On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization (NeurIPS 2024 · similarity 0.87)
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.