Publications
J: Journal or CS conference papers, C: Peer-reviewed conference papers
2023
[J18] Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization [arXiv]
Daesung Kim and Hye Won Chung
Conference on Neural Information Processing Systems (NeurIPS), 2023.
[J17] A Worker-Task Specialization Model for Crowdsourcing: Efficient Inference and Fundamental Limits [arXiv]
Doyeon Kim, Jeonghwan Lee and Hye Won Chung
To appear at IEEE Trans. on Information Theory, 2023.
[J16] Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation [arXiv]
Joonhyuck Yang, Dongphil Shin and Hye Won Chung
International Conference on Machine Learning (ICML), Jun. 2023
[J15] Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing [arXiv]
Hyeonsu Jeong and Hye Won Chung
International Conference on Machine Learning (ICML), Jun. 2023
[J14] Data Valuation without Training of a Model [arXiv]
Nohyun Ki, Hoyong Choi, and Hye Won Chung
International Conference on Learning Representations (ICLR), 2023.
[J13] Test-Time Adaptation via Self-Training with Nearest Neighbor Information [paper]
Minguk Jang, Sae-Young Chung, and Hye Won Chung
International Conference on Learning Representations (ICLR), 2023.
[C17] Graph Matching in Correlated Stochastic Block Models for Improved Graph Clustering
Joonhyuck Yang and Hye Won Chung
IEEE Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA, Oct. 2023.
2022
[J12] Asymptotic Normality of Log-Likelihood Ratio and Fundamental Limit of the Weak Detection for Spiked Wigner Matrices [arXiv]
Hye Won Chung, Jiho Lee and Ji Oon Lee
[J11] Weak Detection in the Spiked Wigner Model with General Rank [arXiv]
Ji Hyung Jung, Hye Won Chung and Ji Oon Lee
[J10] Weak Detection in the Spiked Wigner Model [arXiv]
Hye Won Chung and Ji Oon Lee
IEEE Trans. on Information Theory, vol. 68, issue 11, pp. 7427-7453, Nov. 2022.
[C16] A Generalized Worker-Task Specialization Model for Crowdsourcing: Optimal Limits and Algorithm [arXiv]
Doyeon Kim, Jeonghwan Lee and Hye Won Chung
IEEE International Symposium on Information Theory (ISIT), June 2022.
2021
[J9] Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks [arXiv]
Jinhee Lee*, Haeri Kim*, Youngkyu Hong*, and Hye Won Chung (*:equal contribution)
Conference on Neural Information Processing Systems (NeurIPS), 2021.
[J8] Binary Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm [arXiv]
Daesung Kim and Hye Won Chung
IEEE Trans. on Information Theory, vol. 67, issue 7, pp. 4588-4612, Jul. 2021.
[J7] Detection of Signal in the Spiked Rectangular Models [pmlr]
Ji Hyung Jung, Hye Won Chung and Ji Oon Lee
International Conference on Machine Learning (ICML), Jun. 2021. (Acceptance rate=21%)
[C15] Crowdsourced Labelling for Worker-Task Specialization Model [arXiv]
Doyeon Kim and Hye Won Chung
IEEE International Symposium on Information Theory (ISIT), Jul. 2021.
2020
[J6] Robust Hypergraph Clustering via Convex Relaxation of Truncated MLE [arXiv]
Jeonghwan Lee, Daesung Kim and Hye Won Chung
IEEE Journal on Selected Areas in Information Theory, No. 1, Issue 3, pp. 613-631, Nov. 2020.
[C14] Crowdsourced Classification with XOR Queries: An Efficient Algorithm with Optimal Sample Complexity [arXiv]
Daesung Kim and Hye Won Chung
IEEE International Symposium on Information Theory (ISIT), Jul. 2020.
2019
[J5] Weak Detection of Signal in the Spiked Wigner Model [PMLR]
Hye Won Chung and Ji Oon Lee
International Conference on Machine Learning (ICML), Jun. 2019. (Acceptance rate<22%)
[C13] Shallow Neural Network can Perfectly Classify an Object following Separable Probability Distribution [arXiv]
Youngjae Min and Hye Won Chung
IEEE International Symposium on Information Theory (ISIT), Paris, France, Jul. 2019.
2018
[J4] Unequal Error Protection Querying Policies for the Noisy 20 Questions Problem [arXiv] [related articles at The Michigan Engineering News, Science Daily]
H. W. Chung, B. Sadler, L. Zheng and A. Hero
IEEE Trans. on Information Theory, vol. 64, no. 2, pp. 1105--1131, Feb. 2018.
[C12] Trade-offs between Sample Complexity and Query Difficulty in Crowdsourced Data Acquisition [arXiv]
H. W. Chung, J. O. Lee, D. Kim, A. Hero
IEEE Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA, Oct. 2018.
[C11] Fundamental Limits on Data Acquisition: Trade-offs between Sample Complexity and Query Difficulty [arXiv]
H. W. Chung, J. O. Lee, A. Hero
IEEE International Symposium on Information Theory (ISIT), Vail, CO, USA, Jun. 2018.
[C10] Unequal Error Protection Querying Policies to the Noisy 20 Questions Problem [arXiv]
H. W. Chung, L. Zheng, B. Sadler and A. Hero
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Calgary, Canada, Apr. 2018.
2017
[J3] Bounds on Variance for Unimodal Distributions [arXiv]
H. W. Chung, B. Sadler and A. Hero
IEEE Trans. on Information Theory, vol. 63, no. 11, pp. 6936--6949, Nov. 2017.
[J2] Capacity of Optical Communications over a Lossy Bosonic Channel with a Receiver Employing the Most General Coherent Electro-Optic Feedback Control [arXiv]
H. W. Chung, S. Guha and L. Zheng
Physical Review A, vol. 96, 012320, Jul. 2017.
Before 2017
[J1] Superadditivity of Quantum Channel Coding Rate with Finite Blocklength Quantum Measurements [arXiv]
H. W. Chung, S. Guha and L. Zheng
IEEE Trans. on Information Theory, vol. 62, no. 10, pp. 5938--5959, Oct., 2016.
[C9] Unequal Error Protection Coding Approaches to the Noisy 20 Questions Problem [arXiv]
H. W. Chung, L. Zheng, B. Sadler and A. Hero
IEEE International Symposium on Information Theory (ISIT), pp. 1700--1704, Barcelona, Spain, July 2016.
[C8] Bounds on Variance for Symmetric Unimodal Distributions [arXiv]
H. W. Chung, B. Sadler and A. Hero
IEEE Allerton Conference on Communication, Control, and Computing (Allerton), pp. 1235--1240, Monticello, IL, USA, Oct. 2015.
[C7] Superadditivity of Quantum Channel Coding Rate with Finite Blocklength Quantum Measurements [paper]
H. W. Chung, S. Guha and L. Zheng
IEEE International Symposium on Information Theory (ISIT), pp. 901--905, Hawaii, USA, July 2014.
[C6] Superadditivity of Quantum Channel Coding Rate with Finite Blocklength Quantum Measurements [arXiv]
H. W. Chung, S. Guha and L. Zheng
Conference on Quantum Information Processing (QIP), Barcelona, Spain, Feb. 2014 (poster).
[C5] Superadditivity of Quantum Channel Coding Rate with Finite Blocklength Quantum Measurements [arXiv]
H. W. Chung and L. Zheng
IEEE Allerton Conference on Communication, Control, and Computing (Allerton), pp. 810--817, Monticello, IL, USA, Oct. 2013.
[C4] On Capacity of Optical Channels with Coherent Detection [link]
H. W. Chung, S. Guha and L. Zheng
IEEE Allerton Conference on Communication, Control, and Computing (Allerton), pp. 879--885, Monticello, IL, USA, Sep. 2011 (invited paper).
[C3] On Capacity of Optical Channels with Coherent Detection [link]
H. W. Chung, S. Guha and L. Zheng
IEEE International Symposium on Information Theory (ISIT), pp. 284--288, St. Petersburg, Russia, Aug. 2011.
[C2] Joint Determination of Power and Decoding Order for Successive Inter- and Intra-Cell Interference Cancellation [link]
H. W. Chung, S. W. Jeon, D. H. Park and S. Y. Chung
IEEE International Conference on Advanced Communication Technology (ICACT), pp. 1482--1486, Korea, Feb. 2007.
[C1] Optimum Supply Voltage and Sleep Transistor Sizing for Energy Minimization in Latency-Constrained MTCMOS Circuits
H. W. Chung, E. J. Hong, K. L. Kim and S. H. Cho
International SoC Design Conference (ISOCC), Korea, 2006