ML Debugging

Overview

ML bugs are usually silent — the code runs, but the model is wrong. Debug systematically by isolating which layer is broken: data, optimization, or generalization. Form a hypothesis, test it with the cheapest possible experiment, then move on.

When to use

• Loss is NaN/Inf or stuck.
• Metrics are implausibly high (leakage) or stuck at chance.
• Train/val curves diverge.

First move: can it overfit one batch?

The fastest sanity check in ML. Take a single small batch and train until loss ≈ 0.