liveBook · Manning

Layer sensitivity analysis

As explained in Quantization and Fast Inference

Layer sensitivity analysis measures how perturbing or quantizing individual layers affects model behavior or accuracy.

Layer sensitivity analysis measures how quantizing or perturbing individual layers affects model behavior or accuracy. Run it before choosing a recovery strategy: diffuse failure points toward QAT, while failure concentrated in one layer points toward mixed precision. section 5.6

Diffuse versus concentrated failure

At INT4, ResNet-18 loses 12 percentage points across layers, while BERT-base falls to 50.9% accuracy because of a single FFN layer. These patterns motivate different interventions. section 5.6

How Quantization and Fast Inference covers it

How deep it goes
Connects diffuse or concentrated failure to recovery choices but does not detail the analysis procedure.
Examples
Contrasts diffuse INT4 accuracy loss in ResNet-18 with a single-layer failure in BERT-base.
What you can do after
Diagnose whether quantization failure is diffuse or concentrated to guide recovery-method selection.
How it connects
Links post-training quantization, quantization-aware training, and mixed-precision quantization.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Quantization and Fast Inference. The section links point to the parts of the book it draws on.