Skip to content
conftrace_

maximal update parametrization

3 papers

Explore in graph

Also known as

MUP

Co-occurring keywords · papers mentioning both

neural network hyperparameter (1) zero-shot (1) pdes (1) linearly independent features (1) tensor program framework (1) billion-parameter (1) infinite-width neural network (1) fourier neural operator (1) global minimum (1) model scaling (1)

Papers

Global Convergence and Rich Feature Learning in L-Layer Infinite-Width Neural Networks under μ Parametrization ICML 2025 Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators ICML 2025 Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer NeurIPS 2021