Equivalent Wishart Ansatz for kernel renormalization in Bayesian MLPs and CNNs in the proportional regime, with tests showing good agreement on benchmarks.
Microscopic and collective signatures of feature learning in 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
-
Kernel Renormalization in Bayesian Deep Neural Networks: the Equivalent Wishart Ansatz in the Proportional Regime
Equivalent Wishart Ansatz for kernel renormalization in Bayesian MLPs and CNNs in the proportional regime, with tests showing good agreement on benchmarks.