Research map / Optimization / Nonconvex and smooth optimization
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite 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 asynchronous ProxAsaga with multiple cores instead of its one-core sequential version | ProxAsaga · KDD 2010 | running-time speedup: 11x | Helped |
| Use asynchronous ProxAsaga with multiple cores instead of its one-core sequential version | ProxAsaga · Criteo | running-time speedup: never above 6x | Helped |
| Use ProxAsaga instead of Fista | logistic regression on large sparse datasets · large sparse problems | time to reach 10^-10 suboptimality speed ratio: between 5x and 80x | Helped |
| Use ProxAsaga instead of AsySpcd | logistic regression on large sparse datasets · large sparse problems | time to reach 10^-10 suboptimality speed ratio: between 13x and 290x | Helped |
| Use ProxAsaga instead of competing methods | asynchronous optimization methods · large sparse datasets | running time to reach target suboptimality | Helped |
| Increase dataset sparsity (lower Δ) | ProxAsaga · KDD 2010 and Criteo | running-time speedup: KDD 2010: Δ=0.15, 11x; Criteo: Δ=0.89, never above 6x | Helped |
Closest papers by meaning
- Parallel Asynchronous Stochastic Variance Reduction for Nonconvex Optimization (AAAI 2017 · similarity 0.90)
- Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging (NeurIPS 2019 · similarity 0.90)
- The Sound of APALM Clapping: Faster Nonsmooth Nonconvex Optimization with Stochastic Asynchronous PALM (NeurIPS 2016 · similarity 0.90)
- Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations (NeurIPS 2024 · similarity 0.87)
- Non-convex Stochastic Composite Optimization with Polyak Momentum (ICML 2024 · similarity 0.86)
- Rescaled Asynchronous SGD: Optimal Distributed Optimization under Data and System Heterogeneity (NeurIPS 2026 · 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.