Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning
Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen data. Building on Sharpness-Aware Minimization (SAM), for seeking flat minima associated with improved generalization, we propose the Extragradient-Inspired Sharpness-Aware Minimization (EISAM), a novel optimizer that enhances generalization via the extragradient technique. EISAM uses a two-step update process: a prediction step investigating the geometry of the loss landscape an
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 45%Multi-modal deep learning model for visual acuity prediction from wide field colour fundus imaging - Nature →
- FuzzySimilar title/name (fuzzy) · 87%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.94): “Leveraging Extragradient for Effective Sharpness-Aware Minim” ≈ “aymericdamien/TopDeepLearning””
- FuzzyOverlapping authors or contributors · 62%keras-team/keras →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%HKUDS/LightRAG →
“Shared author/contributor keys: jin”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Yao Fu →
“Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning”
- LinkedLinked via arxiv author · 85%Chunxia Zhang →
“Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning”
- LinkedLinked via arxiv author · 85%Junmin Liu →
“Leveraging Extragradient for Effective Sharpness-Aware Minimization in Deep Learning”