Frank-Wolfe: Why Linear Oracles Beat Projections on Constrained Problems
Constrained optimisation has a quiet asymmetry. Taking a gradient step is usually easy. Staying inside the feasible set is often the hard part. Projected gradient descent assumes you can project any point back onto the set cheaply. For many sets that matter in machine learning, you cannot. The Fran…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-17 15:33 · DEV Community — Machine Learning
Frank-Wolfe: Why Linear Oracles Beat Projections on Constrained Problems