Skip to content
conftrace_

gradient descent initialization

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

linear transformer (1) linear attention (1) multi-layer perceptron (1) linear transformer block (1) bayes optimal (1) approximation error (1) gradient descent (1) in-context learning (1)

Papers

In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization NeurIPS 2024