AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Sharpness-Aware Minimization Can Hallucinate Minimizers

Chanwoong Park, Uijeong Jang, Ernest K. Ryu, Insoon Yang

ICML 2026 · Optimization › Implicit bias and generalization · approach: Sharpness-aware minimization theory

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
add 10% SGD warm-start before SAMSAM · CIFAR-100 ResNet-18 (stochastic, rho=0.3 peak)Test accuracy (%): 77.05 -> 77.49Improved
add short SGD warm-start before SAMSAM · MNIST 2-layer Tanh (full-batch)training loss plateauImproved
add short SGD warm-start before SAMSAM · CIFAR-100 ResNet-18 (stochastic)stability across rhoImproved
increase perturbation radius rho from 1.0SAM · MNIST 2-layer Tanh (full-batch)training loss / test accuracyHurt
increase rho from 0.0 to 0.5 (SAM instead of plain gradient descent)SAM · CIFAR-10 ResNet-18 (full-batch)final training loss f(x_T): 0.001 -> 0.081Hurt
increase rho from 0.0 to 2.0SAM · CIFAR-100 ResNet-18 (full-batch)final training loss f(x_T): 0.009 -> 0.828Hurt
increase rho from 0.0 to 1.5SAM · CIFAR-10 ResNet-18 (full-batch)gradient norm ||grad f(x_T)||: 0.006 -> 11.932Hurt
increase rho from 0.0 to 0.5SAM · CIFAR-100 ResNet-18 (full-batch)shifted gradient norm ||grad f(x_T+)||: 0.058 -> 0.100Mixed

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