[Idea]: Stochastic Gradient Descent (SGD)

[ananyag309]

Idea Title

Stochastic Gradient Descent (SGD)

Idea Description

Stochastic Gradient Descent updates the model's parameters by calculating the gradient of the loss function for a single training example (or a small batch), rather than the entire dataset. This makes it computationally efficient but can lead to noisy updates

Potential Benefits

• [ ] Improves user experience
• [X] Enhances learning
• [ ] Adds a new feature
• [X] Improves code quality
• [ ] Other

Implementation Suggestions (Optional)

No response

[github-actions[bot]]

👋 Hi @ananyag309! Thanks for opening this issue. We appreciate your contribution to the Algo project. Our team will review it soon.