VLDB 2026 Research / reviewers in the wild / expert

Jaewoo Park 0002

dblp:35/3306-2 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
1since 2021 · last 2025
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Learning theory · 50% Probabilistic and Bayesian machine learning · 50%

Topics — the 6 heaviest of 6, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Probabilistic and Bayesian machine learning › deep probabilistic models › bayesian deep learning
bayesian neural networks		 0.912025
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality · NeurIPS 2025
Machine learning › Learning theory
curse of dimensionality		 0.912025
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality · NeurIPS 2025
Machine learning › Probabilistic and Bayesian machine learning › statistical inference › bayesian inference › bayesian asymptotics
posterior contraction rates		 0.912025
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality · NeurIPS 2025
Machine learning › Learning theory
sample complexity		 0.912025
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality · NeurIPS 2025
Machine learning › Probabilistic and Bayesian machine learning › statistical inference › bayesian inference › prior distribution
sparsity prior		 0.912025
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality · NeurIPS 2025
Machine learning › Learning theory
statistical learning theory		 0.912025
Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality · NeurIPS 2025

Methods — techniques the papers use, named apart from their topics

shrinkage prior · 0.9besov space · 0.9bayesian inference · 0.9
YearPublicationVenuePosition
2025 Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality
abstract
This work establishes that sparse Bayesian neural networks achieve optimal posterior contraction rates over anisotropic Besov spaces and their hierarchical compositions. These structures reflect the intrinsic dimensionality of the underlying function, thereby mitigating the curse of dimensionality. Our analysis shows that Bayesian neural networks equipped with either sparse or continuous shrinkage priors attain the optimal rates which are dependent on the intrinsic dimension of the true structures. Moreover, we show that these priors enable rate adaptation, allowing the posterior to contract at the optimal rate even when the smoothness level of the true function is unknown. The proposed framework accommodates a broad class of functions, including additive and multiplicative Besov functions as special cases. These results advance the theoretical foundations of Bayesian neural networks and provide rigorous justification for their practical effectiveness in high-dimensional, structured estimation problems.
Kyeongwon Lee, Lizhen Lin, Jaewoo Park 0002, Seonghyun Jeong
 NeurIPS3