Changho Suh

Associate Professor School of Electrical Engineering Korea Advanced Institute of Science and Technology Room 912, N1 building 291 Daehak-ro, Yuseong-gu Daejeon, South Korea, 34141 +82-42-350-7429 chsuh@kaist.ac.kr Google Scholar Profile

Schedule

Teaching schedule for Spring 2021: EE210 Probability and Introductory Random Processes, Tuesdays and Thursdays 9:00 – 10:15
Office hours: Tuesdays and Thursdays 10:30 – 11:30 (during academic periods)

News (archive)

(Apr. 2021) Kyunghyang Shinmun:

• 2050 Science Odyssey: My vision

• 2050 Science Odyssey: Vision of 14 Scientists

• Book recommendation from scientists

(Mar. 2021) Area Chair of NeurIPS 2021

(Mar. 2021) Steering Committee Member of Y-KAST (2021–2023)

(Mar. 2021) IEEE Information Theory Newsletter March Issue

(Feb. 2021) Contributed a column to KAST's periodical:

• ‘‘Three lessons from Claude Shannon’’ (webite, naver post)

(Feb. 2021) LINKGENESIS Best Teacher Award

• Campus-wide Grand Prize in Teaching

• Honorarium: $10k

(Feb. 2021) Department Teaching Award

• EE424: Introduction to Optimization (Fall 2020)

• Evaluation score: 4.79/5

• Number of registered students: 102

(Feb. 2021) General Chair of the Inaugural IEEE East Asian School of Information Theory 2021

(Feb. 2021) Honoring lifetime achievement of Jong Yong Yun, former CEO of Samsung (youtube, website)

(Jan. 2021) TOP 10 KAIST Research Achievements of 2020 (KAIST Annual R&D Report):

• Fair machine learning (paper, article)

(2021) Papers:

• Y. Roh, K. Lee, S. E. Whang and C. Suh, ‘‘FairBatch: Batch selection for model fairness,’’ ICLR 2021.

• Q. Zhang, V. Y. F. Tan and C. Suh, ‘‘Community detection and matrix completion with social and item similarity graphs,’’ TSP 2021.

• S. Kim, S. Mohajer and C. Suh, ‘‘On the sum capacity of dual-class parallel packet-erasure broadcast channels,’’ TCOM 2021.

(2021) AI and Machine Learning Course

• Oct: Seongnam-KAIST Machine Learning Course (2 days)

• Jul: Hyundai Motor Machine Learning Course (20 days)

• Jun: Hyundai Motor Machine Learning Course (10 days)

• May ~ Oct: SK Hynix Machine Learning Course (16 days)

• Apr: Hyundai Motor Machine Learning Course (10 days)

• Apr: Seongnam-KAIST Machine Learning Course (2 days)

• Feb: Hyundai Motor Machine Learning Course (18 days)

Acknowledgments

• Air Force Office of Scientific Research (AFOSR)

• Google

• National Research Foundation of Korea

• Korea Aerospace Research Institute

• Ministry of Science, ICT & Future Planning

• Electronics and Telecommunications Research Institute

• KaKao

• Samsung

• SKT

• SK-Hynix

• LG

• Hyundai NGV

• Riiid

• Smart Radar System

Selected publications

1. J. Cho, G. Hwang and C. Suh, “A fair classifier using kernel density estimation,” NeurIPS, Dec. 2020 (Top 10 KAIST Research Achievements).

2. H. Kim, K. Lee, G. Hwang and C. Suh, “Crash to not crash: Learn to identify dangerous vehicles using a simulator,” AAAI, Honolulu, USA, Jan. 2019 (oral presentation, website, article, media).

3. K. Ahn, K. Lee, H. Cha and C. Suh, “Binary rating estimation with graph side information,” NeurIPS, Montreal, Canada, Dec. 2018.

4. C. Suh, J. Cho and D. Tse, “Two-way interference channel capacity: How to have the cake and eat it too,” IEEE Transactions on Information Theory, vol. 64, no. 6, pp. 4259–4281, June 2018.

5. S. Mohajer, C. Suh and A. Elmahdy, “Active learning for top-K rank aggregation from noisy comparisons,” ICML, Sydney, Australia, Aug. 2017.

6. Y. Chen, G. Kamath, C. Suh and D. Tse, “Community recovery in graphs with locality,” ICML, New York, USA, June 2016.

7. Y. Chen and C. Suh, “Spectral MLE: Top-K rank aggregation from pairwise comparisons,” ICML, Lille, France, July 2015 (Bell Labs Prize finalist, IEIE Haedong Young Engineer Award).

8. C. Suh, M. Ho and D. Tse, “Downlink interference alignment,” IEEE Transactions on Communications, vol. 59, no. 9, pp. 2616–2626, Sep. 2011 (IEEE Communications Society Stephen O. Rice Prize in 2013).

9. C. Suh and D. Tse, “Feedback capacity of the Gaussian interference channel to within 2 bits,” IEEE Transactions on Information Theory, vol. 57, no. 5, pp. 2667–2685, May 2011 (IEEE ISIT Best Student Paper Award).

10. C. Suh and K. Ramchandran, “Exact-repair MDS code construction using interference alignment,” IEEE Transactions on Information Theory, vol. 57, no. 3, pp. 1425–1442, Mar. 2011 (IEEE ISIT Best Student Paper Award finalist).