Binary neural networks exhibit frequent late-stage compression in the information plane, but compressed representations do not reliably correlate with better generalization performance.
Information bottleneck: Exact analysis of (quantized) neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Information Plane Analysis of Binary Neural Networks
Binary neural networks exhibit frequent late-stage compression in the information plane, but compressed representations do not reliably correlate with better generalization performance.