AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks

Mingze Wang, Chao Ma

NeurIPS 2022 · Optimization › Implicit bias and generalization · approach: Gradient flow and mean-field dynamics · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase network width m from 100 to 1000 (eta=0.01)two-layer ReLU network, GD · CIFAR-10 first 1000realistic loss descent: 3.45\times10^{-1} -> 6.53\times10^{-1}Improved
increase network width m from 100 to 1000 (eta=0.01)two-layer ReLU network, GD · MNIST first 1000realistic loss descent: 3.89\times10^{-1} -> 6.45\times10^{-1}Improved
reduce learning rate from 0.01 to 0.001 (m=200)two-layer ReLU network, GD · CIFAR-10 first 1000realistic loss descent: 4.89\times10^{-1} -> 5.37\times10^{-1}No clear effect
reduce learning rate from 0.01 to 0.001 (m=200)two-layer ReLU network, GD · MNIST first 1000realistic loss descent: 4.78\times10^{-1} -> 4.92\times10^{-1}No clear effect
reduce learning rate from 0.01 to 0.001early-stage bound · hitting iterationiterations to reach bound: 34 -> 346Hurt
change dataset between MNIST and CIFAR-10theoretical loss descent bound · loss descent boundbound value: 2.63\times10^{-1}No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy