Publication

You can also find my papers listed in Google Scholar or dblp.

Preprints

• [P4] Hyeryung Jang, Hyungseok Song, and Yung Yi, "On Cost-efficient Learning of Data Dependency", submitted for journal review, 2019. (Part of this work has been published MOBIHOC 2018)
• [P3] Nicolas Skatchkovsky, Hyeryung Jang, and Osvaldo Simeone, "Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence", submitted for conference publication, 2019. (arXiv preprint version is available at arXiv:1910.09594)
• [P2] Sangwoo Park, Hyeryung Jang, Osvaldo Simeone, and Joonhyuk Kang, "Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning", under the review of IEEE Transactions on Signal Processing (TSP), 2019. (Part of this work has been published SPAWC 2019)
• [P1] Hyeryung Jang, Hyungwon Choi, Yung Yi, and Jinwoo Shin, "Adiabatic Persistent Contrastive Divergence Learning", under the revision of ACM Transactions on Modeling and Performance Evaluation of Computing Systems (TOMPECS), 2019. (Part of this work has been published ISIT 2017)

Journal

• [J4] Hyeryung Jang, Osvaldo Simeone, Brian Gardner, and André Grüning, "An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications", IEEE Signal Processing Magazine (SPM) Special Issue on Learning Algorithms and Signal Processing for Brain-Inspired Computing, vol.36, no.6, pp.64-77, Nov. 2019. (arXiv preprint version is available at arXiv:1910.01059) [post]
• [J3] Hyeryung Jang, Jinwoo Shin, and Yung Yi, "Simulation-based Distributed Coordination Maximization over Networks”, IEEE Transactions on Control of Network Systems (TCNS), vol.6, no.2, pp.713-726, June. 2019. (Part of this work has been published MOBIHOC 2016. arXiv preprint version is available at arXiv:1809.04972)
• [J2] Hyeryung Jang, Se-Young Yun, Jinwoo Shin, and Yung Yi, "Game Theoretic Perspective of Optimal CSMA”, IEEE Transactions on Wireless Communications (TWC), vol.17, no.1, pp.194-209, Jan. 2018. (Part of this work has been published INFOCOM 2014)
• [J1] Hyojung Lee, Hyeryung Jang, Jeong-woo Cho, and Yung Yi, "Traffic Scheduling and Revenue Distribution among Providers in the Internet: Trade-offs and Impacts”, IEEE Journal on Selected Areas in Communications (JSAC) Special Issue on Game Theory for Networks, vol.35, no.2, pp.421-431, Feb. 2017. (Part of this work has been published INFOCOM SDP workshop 2013)

Conference

• [C11] Hyungseok Song, Hyeryung Jang, Hai Hong Tran, Se-eun Yoon, Kyunghwan Son, Donggyu Yun, Hyoju Chung, and Yung Yi, "Solving Continual Combinatorial Selection via Deep Reinforcement Learning", in Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2019. (arXiv preprint version is available at arXiv:1909.03638)
• [C10] Sangwoo Park, Hyeryung Jang, Osvaldo Simeone, and Joonhyuk Kang, "Learning How to Demodulate from Few Pilots via Meta-Learning", in Proceedings of IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 2019. (arXiv preprint version is available at arXiv:1903.02184)
• [C9] Hyeryung Jang, and Osvaldo Simeone, "Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing", in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019. (arXiv preprint version is available at arXiv:1810.08940)
• [C8] Hyeryung Jang, HyungSeok Song, and Yung Yi, "Learning Data Dependency with Communication Cost", in Proceedings of ACM Mobile Ad Hoc Networking and Computing (MOBIHOC), 2018. (Acceptance rate: 16.8%) (arXiv preprint version is available at arXiv:1804.10942) [slide]
• [C7] Hyeryung Jang, Hyungwon Choi, Yung Yi, and Jinwoo Shin, "Adiabatic Persistent Contrastive Divergence Learning", in Proceedings of IEEE International Symposium on Information Theory (ISIT), 2017. (arXiv preprint version is available at arXiv:1605.08174) [slide]
• [C6] Hyeryung Jang, Se-Young Yun, Jinwoo Shin, and Yung Yi, "Distributed Coordination Maximization over Networks: A Stochastic Approximation Approach", in Proceedings of ACM Mobile Ad Hoc Networking and Computing (MOBIHOC), 2016. (Acceptance rate: 18.7%) [slide]
• [C5] Hyeryung Jang, Se-Young Yun, Jinwoo Shin, and Yung Yi, "Distributed Learning for Utility Maximization over CSMA-based Wireless Multihop Networks", in Proceedings of IEEE International Conference on Computer Communications (INFOCOM), 2014. (Acceptance rate: 19.3%) [slide] [video]
• [C4] Hyojung Lee, Hyeryung Jang, Yung Yi, and Jeong-woo Cho, "On the Interaction between Content-Oriented Traffic Scheduling and Revenue Sharing among Providers", in Proceedings of IEEE International Conference on Computer Communications (INFOCOM) Smart Data Pricing workshop, 2013.
• [C3] Jaehoon Jeong, Hyeryung Jang, Yujin Kim, Yung Yi, and Jeonghoon Mo, "Network traffic reduction through smart network", in Proceedings of International Conference on Information Networking (ICOIN), 2013.
• [C2] Hyojung Lee, Hyeryung Jang, and Yung Yi, "On the Stability of ISPs’ Coalition Structure: Shapley Value based Revenue Sharing", in Proceedings of Annual Conference on Information Sciences and Systems (CISS), 2012.
• [C1] Hyeryung Jang, Hyojung Lee, and Yung Yi, "On the Interaction between ISP Revenue Sharing and Network Neutrality", in Proceedings of ACM International Conference on emerging Networking Experiments and Technologies (CONEXT) Student workshop, 2010. [poster]

Thesis

• [T2] Hyeryung Jang, "Optimization and Learning of Graphical Models: A Stochastic Approximation Approach", Ph.D. Thesis in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST), 2017. (Advisor: Prof. Yung Yi, Co-Advisor: Prof. Jinwoo Shin)
  • Abstract: This thesis mainly addresses the problem of optimization and learning in graphical models via stochastic approximation theory. First, in various multi-agent networked environments, the system can benefit from coordinating actions of two interacting agents at some cost of coordination, where a primary goal is to develop distributed algorithms maximizing the coordination effect. Examples include a wireless sensor networks with duty cycling, where a sensor node consumes a certain amount of energy when it is awake, but a coordinated operation of sensors enables some meaningful tasks, e.g., sensed data forwarding. Such pair-wise coordinations and node-wise costs in the network can be captured by graphical model framework, which becomes the problem of finding the optimal graph parameter. In this thesis, I present various distributed algorithms that require only one-hop message passing and locally-observed information, which can be interpreted based on either Lagrange duality theory or game theory framework. The proposed algorithms are motivated by a stochastic approximation method that runs a Markov chain simulation incompletely over time, but provably guarantees the convergence to the optimal solution. Second, I discuss the problem of parameter learning in graphical models having latent variables, where the standard approach, i.e., Expectation Maximization algorithm, is computationally intractable for high dimensional data, in both expectation and maximization steps. Since the substitution of one step to a faster surrogate for combating against intractability can often cause failure in convergence, I propose a new learning algorithm (called Adiabatic Persistent Contrastive Divergence), which runs a few cycles of Markov chains in both steps. Using multi-time-scale stochastic approximation theory, the proposed algorithm provably ensures convergence to a correct optimum, and moreover, I demonstrate the theoretical findings through extensive experiments with synthetic data and/or real-world data sets.
• [T1] Hyeryung Jang, "Economic Benefits of ISP-CDN and ISP-ISP Cooperation", M.S. Thesis in Electrical Engineering from Korea Advanced Institute of Science and Technology (KAIST), 2012. (Advisor: Prof. Yung Yi)

MISC

• 5 Korean conference and journal publications
• [M5] Hyeryung Jang, Yung Yi, and Jinwoo Shin, ”Learning Probabilistic Graphical Models via Stochastic Approximation”, in Proceedings of Joint Conference on Communications and Information (JCCI), 2016.
• [M4] Hyojung Lee, Hyeryung Jang, and Yung Yi, ”Shapley value based ISP Revenue Sharing: Feasibility and Stability”, in Proceedings of Joint Conference on Communications and Information (JCCI), 2013.
• [M3] Jaehoon Jeong, Hyeryung Jang, Yung Yi, Jeonghoon Mo, Hoseok Oh, and Youngil Seo, ”Economic Value of Smart Network”, in Proceedings of Conference on Electronics and Information Communications (CEIC), 2011.
• [M2] Hyeryung Jang, Hyojung Lee, Jeong-woo Cho, and Yung Yi, ”Consolidation on Disintermediation?: Shapley-like Profit Distribution among ISPs”, in Proceedings of Summer Workshop on Computer Communications (SWCC), 2011.
• [M1] Hyojung Lee, Hyeryung Jang, and Yung Yi, ”Shapley Value Mechanism: Revenue sharing among ISPs with CP subsidy”, in Proceedings of Joint Conference on Communications and Information (JCCI), 2011.

Reference Available on Request

• Professor Yung Yi: Professor at the School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea, yiyung at kaist dot edu, +82 (0) 42 350 3486
• Professor Jinwoo Shin: Associate Professor at the School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea, jinwoos at kaist dot ac dot kr
• Professor Osvaldo Simeone: Professor at the Department of Informatics, King's College London (KCL), United Kingdom, osvaldo dot simeone at kcl dot ac dot uk
• Professor Se-Young Yun: Assistant Professor at the Department of Industrial & Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), South Korea, yunseyoung at kaist dot ac dot kr