Aspect ratio of weight matrices biases heavy-tail spectral metrics; the new FARMS subsampling method removes this bias and improves downstream layer-wise tuning.
The neural tangent kernel in high dimensions: Triple descent and a multi-scale theory of generalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
Aspect ratio of weight matrices biases heavy-tail spectral metrics; the new FARMS subsampling method removes this bias and improves downstream layer-wise tuning.