How does batch size affect training (speed, memory, generalization), and how do you scale it?

Batch size is a training knob with non-obvious effects on speed, memory, and generalization. The signal is the large-batch tradeoffs and the learning-rate-scaling and gradient-accumulation tricks that make scaling actually work.

Updated Aug 2026 · Grounded in real Applied AI Engineer interview loops and written to a senior-engineer editorial bar.