Research map / Optimization / Nonconvex and smooth optimization
Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a projection-free first-order method for optimization over general compact convex sets that avoids linear optimization oracles, as the abstract's framing suggests; full text unavailable so details are limited.
Problem
Projection-free optimization over general compact convex sets, where Frank-Wolfe methods are hard to extend because they rely on a linear optimization oracle that is costly for general sets.
Approach
Extends projection-free first-order methods to general compact convex sets without an optimization oracle, aiming for fast convergence and iteration-wise feasibility. Specific mechanism not stated in the available abstract.
Experimental setup
Builds on: Frank-Wolfe
Closest papers by meaning
- Hom-PGD$^+$: Fast Reparameterized Optimization over Non-convex Ball-Homeomorphic Set (ICML 2026 · similarity 0.91)
- A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle (ICML 2024 · similarity 0.87)
- Revisiting Frank-Wolfe for Structured Nonconvex Optimization (NeurIPS 2025 · similarity 0.87)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.87)
- Projection-Free Online Convex Optimization with Time-Varying Constraints (ICML 2024 · similarity 0.87)
- Projection-Free Variance Reduction Methods for Stochastic Constrained Multi-Level Compositional Optimization (ICML 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.