Franck Iutzeler
@franck-iutzeler.bsky.social
Professor of applied mathematics at the University of Toulouse
Website: www.iutzeler.org
Website: www.iutzeler.org
📊 Here's how it looks on a standard non-convex example. We plot the log of the global convergence time as a function of the step-size. Our theory predicts a linear relationship and the slope of this line (red). R² = 0.97 for theory vs 0.99 for data fit ✔️
June 18, 2025 at 1:59 PM
📊 Here's how it looks on a standard non-convex example. We plot the log of the global convergence time as a function of the step-size. Our theory predicts a linear relationship and the slope of this line (red). R² = 0.97 for theory vs 0.99 for data fit ✔️
❓ How long does SGD take to reach the global minimum on non-convex functions?
With W. Azizian, J. Malick, P. Mertikopoulos, we tackle this fundamental question in our new ICML 2025 paper: "The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes"
With W. Azizian, J. Malick, P. Mertikopoulos, we tackle this fundamental question in our new ICML 2025 paper: "The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes"
June 18, 2025 at 1:59 PM
❓ How long does SGD take to reach the global minimum on non-convex functions?
With W. Azizian, J. Malick, P. Mertikopoulos, we tackle this fundamental question in our new ICML 2025 paper: "The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes"
With W. Azizian, J. Malick, P. Mertikopoulos, we tackle this fundamental question in our new ICML 2025 paper: "The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes"