Exercise
Week 3: Linear Regression in PyTorch (4 Questions)
1. Stochastic Gradient Descent
- Exercise: Implement a linear regression model using stochastic gradient descent (SGD) on a synthetic dataset. Plot the loss curve to show convergence over iterations.
2. Mini-Batch Gradient Descent
- Exercise: Modify your SGD implementation to use mini-batch gradient descent. Train the model on a dataset with mini-batches and compare the performance with the full-batch SGD approach.
3. PyTorch Built-in Functions
- Exercise: Use PyTorch's built-in functions (
torch.nn.Linear,torch.optim.SGD) to build and train a linear regression model. Compare the results with your previous implementations.
4. Training and Validation Sets
- Exercise: Split your dataset into training and validation sets. Train a linear regression model on the training set and evaluate its performance on the validation set. Plot the training and validation loss over epochs.