A statistical error analysis framework yields iterative and analytic quantizers that improve accuracy and stability when incorporated into quantization-aware training for integer and floating-point formats.
Fp8 quantization: The power of the exponent.Advances in Neural Information Processing Systems, 35:14651–14662, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
StatQAT: Statistical Quantizer Optimization for Deep Networks
A statistical error analysis framework yields iterative and analytic quantizers that improve accuracy and stability when incorporated into quantization-aware training for integer and floating-point formats.