Changho Suh

Changho Suh 

Associate Professor
School of Electrical Engineering
KAIST

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 Fall 2022: KAIST Life Academy, Friday 14:00 – 18:00
Office hours: Thursday 15:00 – 17:00 (during academic periods)

News (archive)

(Nov. 2022) Elevated to IEEE Fellow:

  • For contributions to interference management and distributed storage codes

(Nov. 2022) A new textbook published (Now Publishers):

convex 

Convex Optimization for Machine Learning
Supported by the Google Education Grant
open access link

(Nov. 2022) A new textbook will be published (Springer):

communication 

Communication Principles for Data Science

(Nov. 2022) Delivered an AI course at KAIST AI Graduate School CAIO program:

  • Fair AI and applications

(Nov. 2022) Delivered an invited talk at Hyundai Motor AI conference:

  • AI for manufacturing

(Nov. 2022) Call for Contributions for IEEE Information Theory Newsletter

  • Deadline: Nov. 30

  • Share any ideas, initiatives, or potential contributions you may have in mind

  • Send contributions to the Newsletter Editor, Changho Suh <chsuh@kaist.ac.kr>

(Aug. 2022) Received the Google Research Award on:

  • Fairness under correlation shifts

(July 2022) Acknowledged during the ISIT 2022 Awards Ceremony for Recognition of:

(June 2021) IEEE Information Theory Newsletter June Issue

(June 2022) Organizer of AI World 2022: Tech & Future:

(June 2022) Delivered an AI course at KAIST AI Graduate School CAIO program:

  • Fair AI and applications

(May 2022) Delivered an invited talk at AI Frontiers Summit:

  • Fair AI and applications

(May 2022) Delivered an invited talk at KAIST AI Graduate School Colloquium:

  • AI and fairness

(May 2022) A paper accepted in IEEE Transactions on Signal Processing:

(Apr. 2022) Two papers accepted in ISIT2022:

  • G. Suh and C. Suh, ‘‘Graph-assisted matrix completion in a multi-clustered graph model’’

  • A. Elmahdy, J. Ahn, S. Mohajer and C. Suh, ‘‘The optimal sample complexity of matrix completion with hierarchical similarity graphs’’

(Apr. 2022) Launched the inaugural issue of the online Information Theory Society Newsletter:

Selected funding agencies

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).