Tian-Hao Guo

When Does Compensating Inherited Quantization Error Help? Mean-Square Guarantees for Layer-Wise Quantization and Their Limits

Layer-wise post-training quantization methods let each layer compensate for the quantization error inherited from earlier layers. We ask under what assumptions such compensation guarantees a network output error no larger than without it. For linear networks of any depth, with the required calibration Gram matrices inv...