New results break with decades of conventional wisdom for the gradient descent algorithm. The post Risky Giant Steps Can Solve Optimization Problems Faster first appeared on Quanta Magazine
Optimization problems can be tricky, but they make the world work better. These kinds of questions, which strive for the best way of doing something, are absolutely everywhere. Your phone’s GPS calculates the shortest route to your destination. Travel websites search for the cheapest combination of flights that matches your itinerary. And machine learning applications, which learn by analyzing…