conftrace_

width

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

depth (2) over-parameterization (1) efficientnet-b0 (1) llama-7b (1) theory (1) differentiable top-k (1) diminishing return (1) model scaling (1) feed-forward network (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 On the Diminishing Returns of Width for Continual Learning ICML 2024