Simone Bombari
5 papers · 2022–2025 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(5)
Core Methods
(3)
Optimization & Theory · Machine Learning
(3)
Deep Learning
(2)
Artificial Intelligence
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Architectures
(1)
Core AI
(1)
Mathematics
(1)
Optimization
(1)
Optimization & Theory · Deep Learning
(1)
Understanding
(1)
Keywords
random feature
(3)
neural tangent kernel
(3)
regularization
(1)
gradient descent
(1)
covariance
(1)
softmax
(1)
stability
(1)
generalization bound
(1)
deep neural network
(1)
spurious correlation
(1)
spurious feature
(1)
eigenvalue bound
(1)
schur complement
(1)
attention layer
(1)
memorization capacity
(1)
word sensitivity
(1)
memorization
(1)
bert-base embeddings
(1)
over-parameterization
(1)
feature alignment
(1)
Papers
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
ICML 2025
How Spurious Features are Memorized: Precise Analysis for Random and NTK Features
ICML 2024
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features
ICML 2024
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels
ICML 2023
Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization
NeurIPS 2022