publications & preprints

See also my Semantic and Google scholar profiles.

• On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets
  Jiashuo Liu ^†, Tianyu Wang ^†, Peng Cui, Hongseok Namkoong
  Under review
  [ code ]
  
  
• Modeling Interference Using Experiment Roll-out
  Ari Boyarsky, Hongseok Namkoong, Jean Pouget-Abadie,
  Conference version appeared in ACM conference on Economics and Computation (EC), 2023
  Under review
  
  
• Adaptive Experimentation at Scale: A Computational Framework for Flexible Batches
  Ethan Che, Hongseok Namkoong
  Under review
  
  
• Diagnosing Model Performance Under Distribution Shift
  Tiffany Cai, Hongseok Namkoong, Steve Yadlowsky
  Conference version appeared in Foundations of Responsible Computing (FORC), 2023
  Under review
  [ code ]
  
  
• Minimax Optimal Estimation of Stability Under Distribution Shift
  Hongseok Namkoong, Yuanzhe Ma, Peter Glynn
  Under revision at Operations Research
  
  
• Model Soups: Averaging Weights of Multiple Fine-tuned Models Improves Accuracy Without Increasing Inference Time
  Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo Lopes, Ari Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, Ludwig Schmidt
  International Conference on Machine Learning (ICML), 2022
  [ code ]
  
  
• Robust Fine-tuning of Zero-shot Models
  Mitchell Wortsman ^†, Gabriel Ilharco ^† Jong Wook Kim, Mike Li, Simon Kornblith, Rebecca Roelofs, Raphael Gontijo Lopes, Hannaneh Hajishirzi, Ali Farhadi, Hongseok Namkoong, Ludwig Schmidt
  International Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  Best paper finalist; full oral presentation
  [ code ]
  
  
• Evaluating Model Performance under Worst-case Subpopulations
  Mike Li, Hongseok Namkoong, Shangzhou Xia
  Conference version appeared in Neural Information Processing Systems (NeurIPS), 2021
  Journal version in preparation
  
  
• Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning
  Hongseok Namkoong^†, Samuel Daulton ^†, Eytan Bakshy
  Under review
  Selected for an oral presentation at the Neurips 2020 OfflineRL Workshop
  
  
• Assessing External Validity Over Worst-case Subpopulations
  Sookyo Jeong, Hongseok Namkoong
  Conference version appeared in Conference on Learning Theory (COLT) 2020 under the title "Robust Causal Inference Under Covariate Shift via Worst-Case Subpopulation Treatment Effects"
  Journal version under review
  [ Talk recording ]     [ code ]
  
  
• Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding
  Hongseok Namkoong^†, Ramtin Keramati ^†, Steve Yadlowsky ^†, Emma Brunskill
  Neural Information Processing Systems (NeurIPS), 2020
  [ Talk recording ]     [ code ]
  
  
• Distributionally Robust Losses against Latent Covariate Mixtures
  John Duchi, Tatsunori Hashimoto, Hongseok Namkoong
  Forthcoming in Operations Research
  [ code ]
  
  
• Learning Models with Uniform Performance via Distributionally Robust Optimization
  John Duchi, Hongseok Namkoong
  Annals of Statistics, 49 (3) 1378--1406, 2021
  
  
• Bounds on the Conditional and Average Treatment Effect in the Presence of Unobserved Confounders
  Steve Yadlowsky, Hongseok Namkoong, Sanjay Basu, John Duchi, Lu Tian
  Annals of Statistics, 50 (5), 2587-2615, 2022
  [ Talk recording ]
  
  
• Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach
  John Duchi, Peter Glynn, and Hongseok Namkoong
  Mathematics of Operations Research, 46 (3) 946--969, 2021
  INFORMS APS Best Student Paper Award
  
  
• Scalable End-to-End Autonomous Vehicle Testing via Rare-Event Simulation
  Matthew O'Kelly^†, Aman Sinha ^†, Hongseok Namkoong^†, John Duchi, Russ Tedrake,
  Neural Information Processing Systems (NeurIPS), 2018
  [ videos ]
  
  
• Generalizing to Unseen Domains via Adversarial Data Augmentation
  Riccardo Volpi ^†, Hongseok Namkoong^†, Ozan Sener , John Duchi, Vittorio Murino, Silvio Savarese
  Neural Information Processing Systems (NeurIPS), 2018
  [ code ]
  
  
• Fairness Without Demographics in Repeated Loss Minimization
  Tatsunori Hashimoto , Megha Srivastava, Hongseok Namkoong, Percy Liang
  International Conference on Machine Learning (ICML), 2018
  ICML Best Paper Runner-up Award
  [ code ]
  
  
• Certifying Some Distributional Robustness with Principled Adversarial Training
  Aman Sinha ^†, Hongseok Namkoong^†, Riccardo Volpi , John Duchi
  Conference version appeared in International Conference on Learning Representations (ICLR), 2018.
  Long version available on arXiv as linked.
  Full oral presentation; top 2% of submissions
  [ code ]
  
  
• Variance Regularization with Convex Objectives
  Hongseok Namkoong, John Duchi
  Conference version appeared in Neural Information Processing Systems (NeurIPS), 2017
  Journal of Machine Learning Research, 20(68):1−55, 2019.
  NeurIPS Best Paper Award
  [ code ]
  
  
• Adaptive Sampling Probabilities for Non-smooth Optimization
  Hongseok Namkoong, Aman Sinha, Steve Yadlowsky, John Duchi
  International Conference on Machine Learning (ICML), 2017
  [ code ]
  
  
• Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences
  Hongseok Namkoong, John Duchi
  Neural Information Processing Systems (NeurIPS), 2016