The authors studied the precision floor of neural networks under post-training quantization (PTQ) and quantization- or noise-aware training (QAT).
Neural network precision floor follows a depth law predicted by amplification
The bit-width at which accuracy collapses scales with depth by a power law whose exponent matches that of a measurable propagation quantity across multiple architectures.
Academic
Ahmad S. Tarawneh
Mutah University
Research Digest··3 min read
The authors define the precision floor of a neural network as the perturbation level or bit-width at which test accuracy falls halfway from full precision to chance.
Why this paper
From Mutah University · Released code
In one line
The precision floor of neural networks follows a power law in depth, predicted by predictive amplification with a constant collapse constant.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§