Seok-Ju (Adam) Hahn

Dear @brainie Hi, could you please clarify what line does the error occur, please? Thank you. p.s.) I will update the whole repo. (i.e., ver 2.0 of this implementation) as...

Isn't it equivalent on the computation graph when taking derivatives? FYI, see implementation (https://flower.dev/docs/apiref-flwr.html#server-strategy-fedprox) of [`flower` package](https://flower.dev). It seems same as the one in this repo.

@Hanc1999 what do you mean W={W1, W2}? Does it mean W is a whole model parameter, followingly W1 is for a weight of 1st layer, and W2 is for a...

@Hanc1999 Thank you for your clarification. I cannot find the content you mentioned in FedProx paper... could you let me know if you have in mind? Pertaining to your CASE-A...

Dear @SpeeeedLee Thank you for your report! Since I don't have much time now, so I think I should take some time to inspect your concerns...! Please understand my situation....

Sorry for super late reply 😢 I've just completed my preliminary PhD defense and also preapring for upcoming ICML 2024 submission. I am going to dig into this issue until...

Sorry for super late reply. as @MaoPopovich kindly said, you should align the device ids with the number of your physical GPU cards.

Sorry for super late reply. I think you might give a wrong path to the configuration file. Please kindly check your config.yaml file.

Sorry for super late reply. In order for reproducing the best performance on CIFAR10 dataset reported in the original paper ([McMahan et al., 2016](https://arxiv.org/abs/1602.05629)), you should modify the hyperparmeter settings....

Sorry for super late reply 😢 I've just completed my preliminary PhD defense and also preapring for upcoming ICML 2024 submission. I am going to dig into this issue until...