Sotabase
Home
Researchers
Career
·
Researcher
,
Samsung Advanced Institute of Technology
2023–
·
Post-doctoral Associate
,
New York University
2020–2023
Publications
(8)
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
International Conference on Learning Representations · 2019
229
cited
Directional Analysis of Stochastic Gradient Descent via von Mises-Fisher Distributions in Deep learning
Neural Information Processing Systems · 2018
8
cited
A Non-monotonic Self-terminating Language Model
International Conference on Learning Representations · 2022
Unsupervised Learning of Initialization in Deep Neural Networks via Maximum Mean Discrepancy
arXiv.org · 2023
Sotabase