Publications [#371239] of Rong Ge

Papers Published

1. Wang, X; Yuan, S; Wu, C; Ge, R, Guarantees for Tuning the Step Size using a Learning-to-Learn Approach, Proceedings of Machine Learning Research, vol. 139 (January, 2021), pp. 10981-10990, ISBN 9781713845065
   (last updated on 2026/01/15)

   Abstract:
   Choosing the right parameters for optimization algorithms is often the key to their success in practice. Solving this problem using a learning-to-learn approach-using meta-gradient descent on a meta-objective based on the trajectory that the optimizer generates-was recently shown to be effective. However, the meta-optimization problem is difficult. In particular, the meta-gradient can often explode/vanish, and the learned optimizer may not have good generalization performance if the meta-objective is not chosen carefully. In this paper we give meta-optimization guarantees for the learning-to-learn approach on a simple problem of tuning the step size for quadratic loss. Our results show that the naïve objective suffers from meta-gradient explosion/vanishing problem. Although there is a way to design the meta-objective so that the meta-gradient remains polynomially bounded, computing the meta-gradient directly using backpropagation leads to numerical issues. We also characterize when it is necessary to compute the meta-objective on a separate validation set to ensure the generalization performance of the learned optimizer. Finally, we verify our results empirically and show that a similar phenomenon appears even for more complicated learned optimizers parametrized by neural networks.