1 citations · 1 across the 2 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Fast Learning Rate Transfer in Shallow Linear Networks at Growing Training Horizons
Mana Sakai, Masaaki Imaizumi
Hyperparameter transfer across model width can substantially reduce the cost of tuning large neural networks, but its behavior when the training horizon grows with width is not ful…
cs.LG2025
Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
Mana Sakai, Ryo Karakida, Masaaki Imaizumi
In modern theoretical analyses of neural networks, the infinite-width limit is often invoked to justify Gaussian approximations of neuron preactivations (e.g., via neural network G…