seniorPyTorch

What is gradient checkpoint recomputation cost complexity?

Updated May 17, 2026

Short answer

Checkpointing reduces memory from O(n) to O(√n) at the cost of recomputing forward passes.

Deep explanation

Instead of storing all activations, only selected checkpoints are stored. During backward pass, missing activations are recomputed, increasing compute cost but significantly reducing memory footprint.

Unlock with a Pro subscription to view this section.

View pricing

Real-world example

No real-world example available yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

Common mistakes

No common mistakes listed yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

Follow-up questions

No follow-up questions available yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

More PyTorch interview questions

View all →