Cheolhyoung Lee

Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models

Kyunghyun Cho, Wanmo Kang, Cheolhyoung Lee, 2019, ICLR.

Directional Analysis of Stochastic Gradient Descent via von Mises-Fisher Distributions in Deep learning pdf

Kyunghyun Cho, Wanmo Kang, Cheolhyoung Lee, 2018, NIPS 2018.

A Non-monotonic Self-terminating Language Model

Kyunghyun Cho, Cheolhyoung Lee, Eugene Choi, 2022, ICLR.

Unsupervised Learning of Initialization in Deep Neural Networks via Maximum Mean Discrepancy

Kyunghyun Cho, Cheolhyoung Lee, 2023, ArXiv.