Insu Han

My new webpage is https://insuhan.github.io (please visit here).

About me (CV)

My name is Insu Han. I am currently a Ph.D. student in the School of Electrical Engineering at Korea Advanced Institute of Science and Technology (KAIST), advised by Jinwoo Shin. I recieved an M.S. in Electrical engineering and a B.S. in Electrical Engineering and Mathematics (minored) from KAIST.

My research interests focus on algorithm design and analysis for large-scale machine learning and its applications.

E-mail: insu.han@kaist.ac.kr

Tel: +82-42-350-7632

Office: IT Bld, N1 917

Education

• M.S., Electrical and Engineering, Korea Advanced Institute of Science and Technology (KAIST)
• B.S., Electrical and Engineering (minored in Mathematics), Korea Advanced Institute of Science and Technology (KAIST)

Experience

• Research Intern at Google NYC, June 2019 - September 2019,

Topic: Diversifying large-scale recommendation

Publications

• Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix, Insu Han, Haim Avron and Jinwoo Shin, preprint
• Stochastic Chebyshev Gradient Descent for Spectral Optimization , Insu Han, Haim Avron and Jinwoo Shin, Neural Information Processing Systems (NIPS) 2018, Spotlight Presentation (168/4856=3.5%)
• Faster Greedy MAP Inference for Determinantal Point Processes, Insu Han, Prabhanjan Kambadur, Kyoungsoo Park and Jinwoo Shin International Conference on Machine Learning (ICML) 2017
• Approximating Spectral Sums of Large-scale Matrices using Stochastic Chebyshev Approximations, Insu Han, Dmitry Malioutov, Haim Avron and Jinwoo Shin, SIAM Journal on Scientific Computing (SISC) 2017 (accepted to appear)
• Large-scale Log-determinant Computation through Stochastic Chebyshev Expansions, Insu Han, Dmitry Malioutov, and Jinwoo Shin, International Conference on Machine Learning (ICML) 2015

Talks

• Stochastic Chebyshev Gradient Descent for Spectral Optimization, spotlight presentation, NeurIPS 18 (video)
• Approximating Spectral Sums of Large-scale Matrices using Stochastic Chebyshev Approximations, invited talk at SIAM Conference on Computational Science and Engineering (CSE) 2017 (slide)
• Large-scale log-determinant computation through stochastic Chebyshev expansions, ICML 2015 (video)