Derivatives of Stochastic Gradient Descent in parametric optimization
This provides theoretical insights for hyperparameter optimization in machine learning, but it is incremental as it builds on existing SGD analysis.
The paper tackles the problem of understanding how derivatives of Stochastic Gradient Descent (SGD) iterates behave with respect to parameters in optimization, showing that these derivatives converge to the derivative of the solution mapping with mean squared error under strong convexity, achieving O(log(k)^2 / k) rates with vanishing step-sizes.
We consider stochastic optimization problems where the objective depends on some parameter, as commonly found in hyperparameter optimization for instance. We investigate the behavior of the derivatives of the iterates of Stochastic Gradient Descent (SGD) with respect to that parameter and show that they are driven by an inexact SGD recursion on a different objective function, perturbed by the convergence of the original SGD. This enables us to establish that the derivatives of SGD converge to the derivative of the solution mapping in terms of mean squared error whenever the objective is strongly convex. Specifically, we demonstrate that with constant step-sizes, these derivatives stabilize within a noise ball centered at the solution derivative, and that with vanishing step-sizes they exhibit $O(\log(k)^2 / k)$ convergence rates. Additionally, we prove exponential convergence in the interpolation regime. Our theoretical findings are illustrated by numerical experiments on synthetic tasks.