Enoch Hyunwook Kang
(I am a Korean. Hyunwook (Ḥănōḵ/חֲנוֹךְ in Hebrew, pronounced Enoch in English) is my first name.)
I am a researcher studying machine learning theory inspired by the practices in market design problems at the University of Washington. I am a Computer Engineering Ph.D.
Research interests
Personalized recommendation
Personalized experimentation
Publications
Personalized recommendation and experimentation
1. "Recommender system as an exploration coordinator: a bounded O(1) regret algorithm for large platforms", Hyunwook Kang, P. R. Kumar, ArXiv Link
Preliminary versions of this work have appeared in:
ICML 2022 Adaptive Experimentation and Active Learning in the Real World (ReALML) workshop
RecSys 2022 Causality, Counterfactuals, Sequential Decision-Making & Reinforcement Learning workshop (Selected as the Long Oral presentation)
2. "Best of both worlds: personalized treatment recommendation with both bounded O(1) regret and robust ITE estimation", Hyunwook Kang and P. R. Kumar, draft to be shared on-demand
3. "Near-equivalence between o(log n) regret and delay robustness in interactive decision-making systems", Hyunwook Kang and P. R. Kumar, draft to be shared on-demand
NeurIPS 2023 Adaptive Experimentation and Active Learning in the Real World (ReALML) workshop
Offline Reinforcement Learning
Hyunwook Kang, P. R. Kumar, "(1-r)-approximate Fitted Q-iteration for problems with large action space, working paper
Reinforcement Learning with Graph Neural Networks
1. Hyunwook Kang, Taehwan Kwon, James R. Morrison, and Jinkyoo Park, "Learning NP-Hard Multi-Agent Assignment Planning using GNN: Inference on a Random Graph and Provable Auction-Fitted Q-learning" [Arxiv, submitted June 2019], Latest version Link, Neural Information Processing Systems (NeurIPS) 2022
ICML 2020 GRL+: novel applications (Workshop version Oral presentation link)
Informs Annual Meeting 2020 (Contributed Long Oral talk)
Services
Game theory and auctions
Reviewer, IEEE Robotics and Automation Letters (RA-L)
Reviewer, IEEE International Conference on Automation Science and Engineering (CASE)
Machine learning
Reviewer, International Conference on Representation Learning (ICLR)
Reviewer, International Conference on Artificial Intelligence and Statistics (AISTATS)
Reviewer, IEEE Transactions on Automation Sciences and Engineering (T-ASE)
Reviewer, Neural Information Processing Systems (NeurIPS)
(Very short) Research Statement
I just enjoy learning anything that helps me better understand whether a tech firm would work or not; my recent interest is in platform tech firms.