Sungyoon Lee

Sungyoon Lee

Seoul National University

H-index: 5

Asia-South Korea

About Sungyoon Lee

Sungyoon Lee, With an exceptional h-index of 5 and a recent h-index of 5 (since 2020), a distinguished researcher at Seoul National University, specializes in the field of Machine Learning, Deep Learning, Adversarial Machine Learning, Optimization, Generalization.

His recent articles reflect a diverse array of research interests and contributions to the field:

Implicit Jacobian regularization weighted with impurity of probability output

Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors

A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution

Bridged adversarial training

Variational cycle-consistent imputation adversarial networks for general missing patterns

Graddiv: Adversarial robustness of randomized neural networks via gradient diversity regularization

A Reparametrization-Invariant Sharpness Measure Based on Information Geometry

Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples

Sungyoon Lee Information

University

Position

___

Citations(all)

126

Citations(since 2020)

126

Cited By

7

hIndex(all)

5

hIndex(since 2020)

5

i10Index(all)

3

i10Index(since 2020)

3

Email

University Profile Page

Seoul National University

Google Scholar

View Google Scholar Profile

Sungyoon Lee Skills & Research Interests

Machine Learning

Deep Learning

Adversarial Machine Learning

Optimization

Generalization

Top articles of Sungyoon Lee

Title

Journal

Author(s)

Publication Date

Implicit Jacobian regularization weighted with impurity of probability output

Sungyoon Lee

Jinseong Park

Jaewook Lee

2023/6/15

Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors

arXiv preprint arXiv:2305.12883

Sungyoon Lee

Sokbae Lee

2023/5/22

A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution

Sungyoon Lee

Cheongjae Jang

2023

Bridged adversarial training

Neural Networks

Hoki Kim

Woojin Lee

Sungyoon Lee

Jaewook Lee

2023/10/1

Variational cycle-consistent imputation adversarial networks for general missing patterns

Pattern Recognition

Woojin Lee

Sungyoon Lee

Junyoung Byun

Hoki Kim

Jaewook Lee

2022/9/1

Graddiv: Adversarial robustness of randomized neural networks via gradient diversity regularization

IEEE Transactions on Pattern Analysis and Machine Intelligence

Sungyoon Lee

Hoki Kim

Jaewook Lee

2022/4/21

A Reparametrization-Invariant Sharpness Measure Based on Information Geometry

Advances in neural information processing systems

Cheongjae Jang

Sungyoon Lee

Frank Park

Yung-Kyun Noh

2022/12/6

Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples

Advances in Neural Information Processing Systems

Sungyoon Lee

Woojin Lee

Jinseong Park

Jaewook Lee

2021/12/6

Lipschitz-certifiable training with a tight outer bound

Advances in Neural Information Processing Systems

Sungyoon Lee

Jaewook Lee

Saerom Park

2020

See List of Professors in Sungyoon Lee University(Seoul National University)

Co-Authors

H-index: 33
Jaewook Lee

Jaewook Lee

Seoul National University

H-index: 31
Sokbae (Simon) Lee

Sokbae (Simon) Lee

Columbia University in the City of New York

H-index: 8
Woojin Lee

Woojin Lee

Seoul National University

H-index: 6
Hoki Kim

Hoki Kim

Seoul National University

academic-engine