Implementation of FedProx aggregation method, taken from "Federated Learning on Non-IID Data Silos: An Experimental Study" paper (https://arxiv.org/pdf/2102.02079.pdf). [x] nlg_gru_fedprox: https://ml.azure.com/runs/8c052875-d053-4e70-b5b6-8f591faf5936?wsid=/subscriptions/d4404794-ab5b-48de-b7c7-ec1fefb0a04e/resourcegroups/gcr-singularity-octo/workspaces/msroctows&tid=72f988bf-86f1-41af-91ab-2d7cd011db47 **Comparison** - DGA ( Acc 0.15, Loss 5.5) ![image.png](https://msktg.visualstudio.com/c507252c-d1be-4d67-a4a1-03b0181c35c7/_apis/git/repositories/0392018c-4507-44bf-97e2-f2bb75d454f1/pullRequests/1578/attachments/image.png) - FedProx ( Acc 0.18, Loss 4.8) ![image (2).png](https://msktg.visualstudio.com/c507252c-d1be-4d67-a4a1-03b0181c35c7/_apis/git/repositories/0392018c-4507-44bf-97e2-f2bb75d454f1/pullRequests/1578/attachments/image%20%282%29.png)