A unified stochastic path-following algorithm with a scaling parameter claims error bounds for quantization, pruning, and their combination, but the defined 1-bit quantizer is not unbiased.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Unified Stochastic Framework for Neural Network Quantization and Pruning
A unified stochastic path-following algorithm with a scaling parameter claims error bounds for quantization, pruning, and their combination, but the defined 1-bit quantizer is not unbiased.