feat(baselines) Add flwr baseline fedht

[chancejohnstone]

Issue

Adding Fed-HT (and FedIter-HT) baseline originally introduced in:

Tong, Q., Liang, G., Zhu, T. and Bi, J., 2020. Federated nonconvex sparse learning. arXiv preprint arXiv:2101.00052.

Description

Fed-HT (and Fed-IterHT) are aggregation strategies for generating highly predictive models while also allowing for constrained sparsity (with some sparsity threshold parameter), instead of just sparsity through regularization. The goal with this baseline is to implement Fed-HT and Fed-IterHT as a custom Flower aggregation strategy and apply to simulated and benchmark datasets from the paper.

Related issues/PRs

This PR is related to the following PR: Add Flower Baseline: FedHT #3987

Proposal

Proposing to merge local fork with Flower repo to include fedht baseline in future Flower versions.

Checklist

• Implement proposed change
• Write tests
• Update documentation
• Make CI checks pass
• Ping maintainers on Slack (channel #contributions)

Comments

Results from paper not reproduced exactly as hyperparameters for figures are not identified. Waiting on response from original authors.

[chancejohnstone]

changed fedht baseline from original to flwr run format