Changho Suh

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 Fall 2020: EE424 Introduction to Optimization, Tuesdays and Thursdays 14:30 - 15:45
Office hours: Tuesdays and Thursdays 16:00 - 17:00 (during academic periods)

News

(July 2020) Received 4.88/5.0 evaluation score for EE321: Communication Engineering (Spring 2020, review quotes).

(July 2020) A paper accepted in ECCV:

(July 2020) Vice-Chair of Electrical Engineering at KAIST.

(July 2020) Associate Editor for Statistical Learning for the IEEE Transactions on Information Theory.

(July 2020) Organizer of AI Camp for middle/high school teachers.

(July 2020) An invited talk at SPCOM:

  • FR-Train: Fair and robust training via information theory

(June 2020) A paper accepted in ICML:

(June 2020) A paper accepted in ECML-PKDD:

(May 2020) Our group introduction video

(May 2020) Guest Editor for the Special Issue of Entropy Journal.

(May 2020) Organizer of Seongnam-KAIST Machine Learning Course:

  • Day 1: Machine learning with scikitlearn

  • Day 2: Deep learning with tensorflow

  • Day 3: Convolutional neural networks

  • Day 4: Recurrent neural networks

(Apr. 2020) Two papers accepted in ISIT:

  • J. Cho, G. Hwang and C. Suh, “A fair classifier using mutual information”

  • Q. E. Zhang, V. Y. F. Tan and C. Suh, “Achievability bounds for community detection and matrix completion with two-sided graph side information”

(Mar. 2020) Elevated to IEEE Senior member.

(Mar. 2020) Delivered an invited talk at University of Minnesota ECE:

  • “Fundamental limits and efficient algorithms for machine learning”

(Feb. 2020) Delivered an invited talk at UC Irvine EECS:

  • “Matrix completion with graph side information”

(Feb. 2020) Delivered an invited talk at ITA:

  • “A fair classifier using mutual information”

(Jan. 2020) Received 4.86/5.0 evaluation score for EE623: Information Theory (Fall 2019)

(Jan. 2020) Received the KAIST Breakthroughs Readers’ Choice Award (article).

(Dec. 2019) Elected as a Member of Young Korean Academy of Science and Technology (Y-KAST).

(Dec. 2019) Director of SK-Hynix Machine Learning Course 2020.

(Nov. 2019) Served as an SPC member of IJCAI 2020 and a TPC member of ISIT 2020.

(Nov. 2019) Received the Google Education Grant.

(Oct. 2019) Appointed as a Distinguished Lecturer for the IEEE Information Theory Society (2020-21)

(Oct. 2019) A paper accepted in NeurIPS Workshop:

  • D. Kim, K. Lee and C. Suh, “Improving model robustness via automatically incorporating self-supervision tasks”

(Sep. 2019) Won the Department Teaching Award:

  • EE523: Convex Optimization (Spring 2019, evaluation score: 4.63/5)

(Sep. 2019) Delivered two-day lectures for Samsung Machine Learning Course:

  • Day 1: Convolutional neural networks

  • Day 2: Recurrent neural networks

(Aug. 2019) A paper accepted in Allerton:

(July 2019) A paper accepted in IT:

(June/July 2019) Delivered three-day lectures for SK-Hynix Machine Learning Course:

  • Day 1: Machine learning and optimization

  • Day 2: Deep learning and optimization

  • Day 3: Robustness and fairness

(June 2019) Delivered invited talks at NUS:

  • “Learn to identify dangerous vehicles using a computer game”

  • “Matrix completion with graph side information”

(May 2019) Delivered an invited talk at LSIT (video):

  • “Matrix completion with graph side information”

(May 2019) A paper accepted in IT:

(Apr. 2019) Received a two-year grant from Air Force Office of Scientific Research (AFOSR):

  • “Validating simulator-based learning via interpretation”

Acknowledgments

Selected publications

  1. Y. Roh, K. Lee, S. Whang and C. Suh, “FR-Train: A mutual information-based approach to fair and robust training”, ICML, Vienna, Austria, July 2020.

  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).

  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).

  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).