Skip to content
conftrace_

depth

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

width (2) generalization (2) over-parameterization (1) efficientnet-b0 (1) llama-7b (1) memorization (1) differentiable top-k (1) attention layer (1) model scaling (1) implicit bia (1)

Papers

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks ICML 2024 Differentiable Model Scaling using Differentiable Topk ICML 2024 What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks ICML 2024