Hyeryung Jang

Hyeryung Jang

Assistant Professor


Department of Artificial Intelligence

Dongguk University

30, Pildong-ro 1-gil, Jung-gu, Seoul, South Korea (04620)

hyeryung.jang_at_dgu.ac.kr 

hrjang357_at_gmail.com

Curriculm Vitae

Google Scholar

LinkedIn

About

I am currently an assistant professor in the Department of Artificial Intelligence at Dongguk University (DGU), Seoul, South Korea, since March 2021. I received my Ph.D. in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST), South Korea, in 2017, under the supervision of Prof. Yung Yi and Prof. Jinwoo Shin. I received my M.S. and B.S. in EE from KAIST in 2012 and 2010, respectively. Prior to joining Dongguk University, I have been a research associate in the Department of Informatics at King's College London (KCL), United Kingdom, working with Prof. Osvaldo Simeone. At DGU, I lead the ION research group (Intelligence and Optimization in Networks). 

Research 

My recent research interests lie in mathematical modeling and analysis of communication systems, with a specific focus on applying learning, inference, and control of probabilistic graphical models to communication systems. More generally, the research area covered by my recent and future works is Networked Machine Learning, which takes inspiration from the human brain to carry out supervised, unsupervised, and reinforcement learning tasks in large-scale communication networks. My past research works include network economics, game theory, and distributed algorithms in communication networks. Here are a few examples of my recent/past research topics.

Learning for Brain-inspired Computing - learning algorithms for dynamic exponential family models [ICASSP2019], for probabilistic Spiking Neural Networks [SPM2019, ICPR2020, ICASSP2021, DSLW2021, NeurIPS2021, COMML2021], and for resource-efficient federated learning [ICASSP2020]

Learning and Inference of Graphical Models (with applications to large-scale networks) - algorithms for communication efficient structure learning [TNET2022, MOBIHOC2018], for sampling efficient reinforcement learning [IJCAI2019], for fast adaptable parameter learning [TSP2021, SPAWC2019], and for multi time-scale parameter learning [ISIT2017]

Optimal and Distributed Parameter Control in Graphical Models - optimal CSMA [INFOCOM2014, TWC2018], coordination maximization [MOBIHOC2016, TCNS2019]

Game Theory and Economics: Networked Market - network economics, pricing of ISPs [JSAC2017, SDP2013]

Education

Work Experiences

Honors and Awards

Project Experiences

Presentation Experiences

Teaching Experiences

Reference Available on Request