Learning Rate Adaptation for Federated and Differentially Private Learning
This addresses the challenge of optimizing learning rates in federated and differentially private settings, offering a practical solution for machine learning practitioners, though it is incremental as it builds on existing SGD methods.
The paper tackles the problem of learning rate tuning in stochastic gradient descent without a validation set by proposing an adaptive algorithm based on extrapolation, showing it is competitive with manual tuning in differentially private training and robust in federated learning.
We propose an algorithm for the adaptation of the learning rate for stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation: to get an estimate for the error against the gradient flow which underlies SGD, we compare the result obtained by one full step and two half-steps. The algorithm is applied in two separate frameworks: federated and differentially private learning. Using examples of deep neural networks we empirically show that the adaptive algorithm is competitive with manually tuned commonly used optimisation methods for differentially privately training. We also show that it works robustly in the case of federated learning unlike commonly used optimisation methods.