Research map / Optimization / Optimizers
Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures
Zhaozhuo Xu, Zhao Song, Anshumali Shrivastava
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 |
|---|---|---|---|
| replace exact greedy direction search with LSH-based approximate MaxIP in Frank-Wolfe | Frank-Wolfe · complexity analysis | cost per iteration | Improved |
| replace exact search with LSH MaxIP in kernel herding | Herding · complexity analysis | cost per iteration | Improved |
| replace exact search with LSH MaxIP in projection-free policy gradient | Policy gradient · complexity analysis | cost per iteration | Improved |
Closest papers by meaning
- On the Bias-Variance-Cost Tradeoff of Stochastic Optimization (NeurIPS 2021 · similarity 0.86)
- On the Role of Batch Size in Stochastic Conditional Gradient Methods (ICML 2026 · similarity 0.85)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · similarity 0.85)
- Learning Complexity of Gradient Descent and Conjugate Gradient Algorithms (AAAI 2025 · similarity 0.85)
- BayeSQP: Bayesian Optimization through Sequential Quadratic Programming (NeurIPS 2025 · similarity 0.84)
- Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions (ICML 2024 · similarity 0.84)
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.
