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 pricingReal-world example
No real-world example available yet.
Unlock with a Pro subscription to view this section.
Upgrade to ProCommon mistakes
No common mistakes listed yet.
Unlock with a Pro subscription to view this section.
Upgrade to ProFollow-up questions
No follow-up questions available yet.
Unlock with a Pro subscription to view this section.
Upgrade to Pro