Changho Suh
 |
Associate Professor Room 912, N1 building +82-42-350-7429 |
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
(Oct. 2020) An invited talk at LG Display AI Workshop:
Machine learning with small data
(Sep. 2020) Won the Department Teaching Award:
EE321: Communication Engineering (Spring 2020, evaluation score: 4.88/5.0, review quotes).
(Sep. 2020) Delivered an invited talk at Edtech Korea Forum
AI fundamentals & curriculums
(2020) Recognition
July: Vice-Chair of Electrical Engineering at KAIST.
July: Associate Editor for Statistical Learning for the IEEE Transactions on Information Theory.
May: Guest Editor for the Special Issue of Entropy Journal.
Mar: Elevated to IEEE Senior member.
Jan: Received 4.86/5.0 evaluation score for EE623: Information Theory (Fall 2019)
Jan: Received the KAIST Breakthroughs Readers’ Choice Award (article).
(2020) AI and Machine Learning Courses
June ~ Nov: SK-Hynix Machine Learning Course (16 days)
Dec: Hyundai Motor Machine Learning Course (10 days)
Oct: Hyundai Motor Machine Learning Course (10 days)
Aug: Seongnam-KAIST Machine Learning Course (2 days)
July: AI Camp for middle/high school teachers (1 day)
May: Seongnam-KAIST Machine Learning Course (2 days)
(2020) Talks
July: Invited talk at SPCOM (“FR-Train: Fair and robust training via information theory”)
Mar: Invited talk at University of Minnesota ECE (“Fundamental limits and efficient algorithms for machine learning”)
Feb: Invited talk at UC Irvine EECS (“Matrix completion with graph side information”)
Feb: Invited talk at ITA (“A fair classifier using mutual information”)
(2020) Papers
Y. Roh, K. Lee, S. Whang and C. Suh, “FR-Train: A mutual information-based approach to fair and robust training,” ICML, Aug. 2020
K. Lee, C. Suh and K. Ramchandran, “Reprogramming GANs via input noise design,” ECML-PKDD, Sep. 2020
M. Kang, K. Lee, Y. H. Lee and C. Suh, “Autoencoder-based graph construction for semi-supervised learning,” ECCV, Aug. 2020
J. Cho, G. Hwang and C. Suh, “A fair classifier using mutual information,” ISIT, June 2020
Q. E. Zhang, V. Y. F. Tan and C. Suh, “Achievability bounds for community detection and matrix completion with two-sided graph side information,” ISIT, June 2020
(2019) Recognition
Dec: Member of Young Korean Academy of Science and Technology (Y-KAST)
Nov: Received the Google Education Grant
Oct: Distinguished Lecturer for the IEEE Information Theory Society (2020-21)
Sep: Won the Department Teaching Award (EE523: Convex Optimization, evaluation score: 4.63/5.0)
Apr: Received a two-year grant from AFOSR (“Validating simulator-based learning via interpretation”)
(2019) Papers
D. Kim, K. Lee and C. Suh, “Improving model robustness via automatically incorporating self-supervision tasks,” NeurIPS Workshop, Dec. 2019.
J. Cho and C. Suh, “Wasserstein GAN can perform PCA,” Allerton, Oct. 2019.
S. Shin and C. Suh, “Two-way function computation,” IEEE Transactions on Information Theory, Feb. 2020.
K. Ahn, K. Lee and C. Suh, “Community recovery in hypergraphs,” IEEE Transactions on Information Theory, Oct. 2019.
(2019) Talks
Sep: Two-day lectures for Samsung Machine Learning Course
July: Three-day lectures for SK-Hynix Machine Learning Course
June: Invited talk at NUS (“Learn to identify dangerous vehicle using a computer game”)
June: Invited talk at NUS (“Matrix completion with graph side information”)
May: Invited talk at LSIT (video) ("Matrix completion with graph side information)
Mar: Invited talk at Samsung Medical Center (“Search engine for medical images”)
Mar: Invited talk at AFOSR (“Interpretable collision avoidance systems for autonomous driving”)
Feb: Invited talk at ITA (“Match prediction from group-wise comparisons”)
Acknowledgments
Selected publications
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.
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).
K. Ahn, K. Lee, H. Cha and C. Suh, “Binary rating estimation with graph side information”, NeurIPS, Montreal, Canada, Dec. 2018.
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.
S. Mohajer, C. Suh and A. Elmahdy, “Active learning for top-K rank aggregation from noisy comparisons”, ICML, Sydney, Australia, Aug. 2017.
Y. Chen, G. Kamath, C. Suh and D. Tse, “Community recovery in graphs with locality”, ICML, New York, USA, June 2016.
Y. Chen and C. Suh, “Spectral MLE: Top-K rank aggregation from pairwise comparisons”, ICML, Lille, France, July 2015 (Bell Labs Prize finalist).
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).
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).
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).