Search Results for author:
Found 2 papers, 0 papers with code
Effective Interplay between Sparsity and Quantization: From Theory to Practice
In addition, through rigorous analysis, we demonstrate that sparsity and quantization are not orthogonal; their interaction can significantly harm model accuracy, with quantization error playing a dominant role in this degradation.
Accuracy Booster: Enabling 4-bit Fixed-point Arithmetic for DNN Training
Based on our findings, we propose Accuracy Booster, a mixed-mantissa HBFP technique that uses 4-bit mantissas for over 99% of all arithmetic operations in training and 6-bit mantissas only in the last epoch and first/last layers.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
