mnist.py uses a CNN for classification of the MNIST dataset. It also includes details of saving network state to file and reloading. The code is based on the following tutorials.

• CNN in PyTorch
• CNN in PyTorch
• Computing the output dimensions of network layers
• MNIST in PyTorch

dssgd.py implements Distributed Selective Stochastic Gradient Descent implemented on the MNIST dataset.

Currently supported parameters are as follows :-

1. trainers : number of participants in DSSGD
2. partition_ratio : part of data sets available to individual participant.
3. n_parts : number of times global update happens per epoch
4. theta : fraction to total parameters updated to global state
5. n_epochs : number of epochs used for training The usual SGD parameters are also present : batch_size_train, batch_size_test, learning_rate, momentum and
   log_interval.

Create a folder results in the same directory to store the trained models and optimizers.