AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Rethinking Neural Network Learning Rates: A Stackelberg Perspective

Sihan Zeng, Sujay Bhatt, Sumitra Ganesh

ICML 2026 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 0 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
use a larger learning rate for the final layer than the body (two-time-scale updates)two-layer ReLU network, synthetic regression with SGD · Synthetic regression (objective f(M_k, w_k))objective valueImproved
evaluate body update on the Stackelberg objective instead of the joint objectivetwo-layer ReLU network, early training · Synthetic regression landscapelargest Hessian eigenvalue: 2.8 -> 21.9 (iteration 5)Improved
curvature advantage late in trainingStackelberg objective · Synthetic regression landscapelargest Hessian eigenvalue: 19.4 vs 17.9 (iteration 200)No clear effect
non-uniform learning rates instead of uniform small (alpha) (ablation)regression, classification, Atari DQN with RMSProp · Friedman, Housing, MNIST, Fashion, CIFAR10, Ataritraining/performance curvesImproved
scale all layers up to the larger learning rate (uniform large) instead of non-uniform (ablation)regression, classification, Atari DQN with RMSProp · Friedman, Housing, MNIST, Fashion, CIFAR10, Ataristability / final performanceHurt
non-uniform learning rates versus uniform rates on some problemsneural network training · generalperformanceNo 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