Sungyoon Lee
7 papers · 2020–2025 · 4 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(22)
Venues
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory · Machine Learning
(7)
Deep Learning
(5)
Optimization & Theory · Deep Learning
(5)
Artificial Intelligence
(2)
Core AI
(2)
Learning Types · Machine Learning
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Architectures
(1)
Domain-Specific
(1)
Learning Types · Deep Learning
(1)
Resources & Methods
(1)
Statistics
(1)
Keywords
loss landscape
(2)
sharpness measure
(2)
stochastic gradient descent
(2)
robust classification
(1)
neural network optimization
(1)
time series
(1)
information geometry
(1)
learning rate
(1)
interval bound propagation
(1)
implicit regularization
(1)
adversarial example
(1)
ridgeless regression
(1)
generalization performance
(1)
verifiable training
(1)
batch size
(1)
prediction risk
(1)
least squares estimator
(1)
edge of stability
(1)
training instability
(1)
jacobian regularization
(1)
Papers
Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors
ICLR 2025
Variance Sensitivity Induces Attention Entropy Collapse and Instability in Transformers
EMNLP 2025
A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution
ICLR 2023
Implicit Jacobian regularization weighted with impurity of probability output
ICML 2023
A Reparametrization-Invariant Sharpness Measure Based on Information Geometry
NeurIPS 2022
Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples
NeurIPS 2021
Lipschitz-Certifiable Training with a Tight Outer Bound
NeurIPS 2020