Dynamical systems (DS) theory is fundamental for many areas of science and engineering. It can provide deep insights into the behavior of systems evolving in time, as typically described by differential or recursive equations.

Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of the data across different clients which can cause a client drift phenomenon.

Weheldoutavalidation setfromthetraining set,andusedthisvalidation settoselecttheL2 regularization hyperparameter,which weselected from 45logarithmically spaced values between 10 6 and 105, applied to the sum of the per-example losses. Because the optimization problem is convex, we used the previous weights as a warm start as we increased theL2 regularization hyperparameter. Wemeasured eithertop-1ormean per-class accuracy, depending on which was suggested by the dataset creators. A.3 Fine-tuning In our fine-tuning experiments in Table 2, we used standard ImageNet-style data augmentationand trained for 20,000 steps with SGD with momentum of0.9 and cosine annealing [ 20]without restarts. Each curve represents a different model.

We design a suite of benchmarks to evaluate the quality of the generated MILP instances.

We design a suite of benchmarks to evaluate the quality of the generated MILP instances.

This paper presents a unifying framework for heterogeneous FL algorithms with online model extraction and provides a general convergence analysis for the first time.

This paper presents a unifying framework for heterogeneous FL algorithms with online model extraction and provides a general convergence analysis for the first time.