Seonghyun Jeong

collaborators

3 papers

math.ST2025

$L_{2}$ -norm posterior contraction in Gaussian models with unknown variance

Seonghyun Jeong

The testing-based approach is a fundamental tool for establishing posterior contraction rates. Although the Hellinger metric is attractive owing to the existence of a desirable tes…

stat.ML2025

Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality

Kyeongwon Lee, Lizhen Lin, Jaewoo Park +1

This work establishes that sparse Bayesian neural networks achieve optimal posterior contraction rates over anisotropic Besov spaces and their hierarchical compositions. These stru…

cs.LG2024

ADOPT: Modified Adam Can Converge with Any $β_{2}$ with the Optimal Rate

Shohei Taniguchi, Keno Harada, Gouki Minegishi +7

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $β_{2}$ ,…

L2​-norm posterior contraction in Gaussian models with unknown variance

Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality

ADOPT: Modified Adam Can Converge with Any β2​ with the Optimal Rate

$L_{2}$ -norm posterior contraction in Gaussian models with unknown variance

ADOPT: Modified Adam Can Converge with Any $β_{2}$ with the Optimal Rate