Probability and Optimization with Applications
Wanmo Kang (강완모)
Professor
Department of Mathematical Sciences
Korea Advanced Institute of Science and Technology (KAIST)
Daejeon, Republic of Korea
wanmo DOT kang AT kaist DOT ac DOT kr
Research Interests
Applied Probability and Stochastic Simulation
Optimization in Stochastic Environments
Applications in Risk Analysis and Machine Learning
Papers
Diffusion Rejection Sampling (with Byeonghu Na, Yeongmin Kim, Minsang Park, Donghyeok Shin, and Il-Chul Moon), ICML (41st, Poster Presentation), 2024 [link]
Label-Noise Robust Diffusion Models (with Byeonghu Na, Yeongmin Kim, Heesun Bae, Junghyun Lee, Se Jung Kwon, and Il-Chul Moon), ICLR (12th, Poster Presentation), 2024 [link]
Training Unbiased Diffusion Models from Biased Datasets (with Yeongmin Kim, Byeonghu Na, Minsang Park, JoonHo Jang, Dongjun Kim, and Il-Chul Moon), ICLR (12th, Poster Presentation), 2024 [link]
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models (with Dongjun Kim, Yeongmin Kim, Se Jung Kwon, and Il-Chul Moon), ICML (40th, Oral Presentation), 2023 [link]
SAAL: Sharpness-Aware Active Learning (with Yoon-Yeong Kim, Youngjae Cho, JoonHo Jang, Byeonghu Na, Kyungwoo Song, and Il-Chul Moon), ICML (40th, Poster Presentation), 2023 [link]
Sequential Likelihood-Free Inference with Neural Proposal (with Dongjun Kim, Kyungwoo Song, Yongjin Shin, Il-Chul Moon, and Weongyoung Joo), Pattern Recognition Letters, 169(May):102-109, 2023 [link]
Maximum Likelihood Training of Implicitly Nonlinear Diffusion Models (with Dongjun Kim, Byeonghu Na, Se Jung Kwon, Dongsoo Lee, and Il-Chul Moon), NeurIPS (36th, Poster Presentation), 2022 [link]
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation (with Dongjun Kim, Seungjae Shin, Kyungwoo Song, and Il-Chul Moon), ICML (39th, Poster Presentation), 2022 [link]
Improved Regret Bounds of Bilinear Bandits using Action Space Analysis (with Kyoungseok Jang, Kwang-Sung Jun, and Se Young Yun), ICML (38th, Poster Presentation), 2021 [link]
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder (with Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song, Weonyoung Joo, and Il-Chul Moon), AAAI Conference (35th, Poster Presentation), 2021 [link]
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models (with Cheolhyoung Lee and Kyunghyun Cho), ICLR (8th, Poster Presentation), 2020 [link]
Unbiased Sensitivity Estimation of One-Dimensional Diffusion Processes (with Jong Mun Lee), Mathematics of Operations Research, 44(1):334-353, 2019 [link]
Directional Analysis of Stochastic Gradient Descent via von Mises-Fisher Distributions in Deep Learning (with Cheolhyoung Lee and Kyunghyun Cho), NeurIPS (32nd, Workshop Presentation), 2018 [link]
Exact Simulation of the Wishart Multidimensional Stochastic Volatility Model (with Chulmin Kang and Jong Mun Lee), Operations Research, 65(5): 1190-1206, 2017 [link]
Design of Informal Finance System: A Case of ROSCA (with Deung-Geon Ahn, Kyoung-Kuk Kim, and Hayong Shin), The Engineering Economist, 62(3):197-230, 2017 [link]
Risk Propagation through a Platform: the Failure Risk Perspective on Platform Sharing (with Yoo S. Hong, Woonghee Tim Huh, and Changmuk Kang), IEEE Transactions on Engineering Management, 62(3):372-383, 2015 [link]
Stress Scenario Selection by Empirical Likelihood (with Paul Glasserman and Chulmin Kang), Quantitative Finance, 15(1):25-41, 2015 [link], also available at OFR Working Paper Series
Design of Risk Weights (with Paul Glasserman), Operations Research, 62(6):1204-1220, 2014 [link], also available at OFR Working Paper Series. See also an article introducing this paper by Edieal J. Pinker [pdf]. Comment by Darrell Duffie [pdf] and Jean-Charles Rochet [pdf]
Information on Jump Sizes and Hedging (with Kiseop Lee), Stochastics, 86(6):889-905, 2014 [link]
Robustness of Order-up-to Policies in Lost Sales Inventory Systems (with Marco Bijvank, Woonghee Tim Huh, and Ganesh Janakiraman), Operations Research, 62(5):1040-1047, 2014 [link]
Large Deviations for Affine Diffusion Processes on R+m × Rn (with Chulmin Kang), Stochastic Processes and their Applications, 124(6):2188–2227, 2014 [link]
Fairing the Gamma: An Engineering Approach to Sensitivity Estimation (with Kyoung-Kuk Kim and Hayong Shin), IIE Transactions, 46(4):374-396, 2014 [link]
Transform Formulae for Linear Functionals of Affine Processes and their Bridges on Positive Semidefinite Matrices (with Chulmin Kang), Stochastic Processes and their Applications, 123(6):2419–2445, 2013 [link]
Denoising Monte Carlo Sensitivity Estimates (with Kyoung-Kuk Kim and Hayong Shin), Operations Research Letters, 40(3):195–202, 2012 [link]
Fast Simulation of Multifactor Portfolio Credit Risk (with Paul Glasserman and Perwez Shahabuddin), Operations Research, 56(5):1200–1217, 2008 [link]
Large Deviations in Multifactor Portfolio Credit Risk (with Paul Glasserman and Perwez Shahabuddin), Mathematical Finance, 17(3):345–379, 2007 [link]
Exploiting Regenerative Structure to Estimate Finite Time Averages Via Simulation (with Perwez Shahabuddin and Ward Whitt), ACM Transactions on Modeling and Computer Simulation (TOMACS), 17(2):Article 8, 2007 [link]
Price Competition with the Attraction Demand Model: Existence of Unique Equilibrium and Its Stability (with Guillermo Gallego, Woonghee Tim Huh, and Robert Phillips), Manufacturing and Service Operations Management (M&SOM), 8(4):359–375, 2006 [link]
Inverse Conic Programming with Applications (with Garud Iyengar), Operations Research Letters, 33(3):319–330, 2005 [link]
Fast Simulation of Multifactor Portfolio Credit Risk in the t-Copula Model (with Perwez Shahabuddin), Proc. Winter Simulation Conf., 1859–1868, 2005 [link]
Working Papers
Collaborative Filtering via User Feedbacks (with Kihui Lee and Se-Young Yun)
Coauthors
Guillermo Gallego (IEOR department at Columbia University)
Paul Glasserman (Columbia Business School)
Woonghee Tim Huh (Sauder School of Business, UBC)
Garud Iyengar (IEOR department at Columbia University)
Kyoungseok Jang (Post Doc., Department of Computation, University of Arizona)
Chulmin Kang (NIMS, Republic of Korea)
Kyoung-Kuk Kim (ISysE department at KAIST)
Cheolhyoung Lee (Post Doc., NYU)
Jong Mun Lee (Meritz Fire & Marine Insurance Co., Ltd)
Kiseop Lee (Mathematics department at University of Louisville)
Il-Chul Moon (ISysE department at KAIST)
Robert Phillips (Columbia Business School)
Perwez Shahabuddin (deceased)
Hayong Shin (ISysE department at KAIST)
Ward Whitt (IEOR department at Columbia University)
Industrial Collaborations