Mohamad Amin Mohamadi
4 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Bronze
πΊοΈ
Taxonomy Completionist
(10)
β
The Questioner
Venues
Top co-authors
Research topics
Keywords
neural tangent kernel
(2)
representation learning
(1)
convergence analysis
(1)
loss landscape
(1)
kernel approximation
(1)
gradient descent
(1)
acquisition function
(1)
adam optimizer
(1)
language model
(1)
coordinate-wise adaptivity
(1)
approximation theory
(1)
network initialization
(1)
pool-based learning
(1)
model retraining
(1)
infinite-width limit
(1)
kernel regime
(1)
look-ahead strategy
(1)
modular addition
(1)
overfitting
(1)
grokking
(1)
Papers
Adam Exploits β_β-geometry of Loss Landscape via Coordinate-wise Adaptivity
ICLR 2025
Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
ICML 2024
A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel
ICML 2023
Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels
NeurIPS 2022