Mirror Descent: Why the Right Geometry Changes Gradient Descent
Gradient descent is usually taught as if it were geometry-free. You compute a gradient, you step in the opposite direction, and you repeat. That picture hides a choice that matters more than the step size: what does "opposite direction" even mean? In Euclidean space, the answer is obvious. In a pro…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-17 17:35 · DEV Community — Machine Learning
Mirror Descent: Why the Right Geometry Changes Gradient Descent