Skip to main content

🏢 Université Paul Sabatier

Derivatives of Stochastic Gradient Descent in parametric optimization
·1733 words·9 mins· loading · loading
AI Generated AI Theory Optimization 🏢 Université Paul Sabatier
Stochastic gradient descent’s derivatives, crucial for hyperparameter optimization, converge to the solution mapping derivative; rates depend on step size, exhibiting O(log(k)²/k) convergence with van…