Batch size directly influences gradient noise and optimization dynamics.

Smaller batches introduce stochasticity that can help generalization, while larger batches provide stable but potentially brittle updates.

Changing batch size without adjusting learning rate often breaks convergence. If you increase batch size, scale the learning rate proportionally or use adaptive optimizers.

Common mistakes:

1. Changing batch size mid-training

2. Comparing results across different batch regimes

3. Assuming larger batches are always better

Batch size is a training hyperparameter, not just a performance knob.