Publications
* corresponding author · underlined names are group members and alumni · (α–β) alphabetical author order
Preprints
Constrained Online Convex Optimization without Slater's Condition
Kihyun Yu, Junehee Lee, Dabeen Lee*
Preprint
arXiv
· June 2026
arXiv
Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret
Seoungbin Bae, Dabeen Lee*
Preprint
arXiv
· June 2026
arXiv
Learning weakly communicating average-reward CMDPs: strong duality and improved regret
Kihyun Yu, Beomhan Baek, Dabeen Lee*
Preprint
arXiv
· May 2026
arXiv
Chebyshev center-based direction selection for multi-objective optimization and training PINNs
Hoyeol Yoon, Seoungbin Bae, Nam Ho-Nguyen, Dabeen Lee*
Preprint
arXiv
· May 2026
arXiv
Logistic bandits with Õ(√dT) regret without context diversity assumptions
Seoungbin Bae, Dabeen Lee*
Preprint
arXiv
· April 2026
arXiv
Learning to route and schedule LLMs from user retrials via contextual queueing bandits
Seoungbin Bae, Junyoung Son, Dabeen Lee*
Preprint
arXiv
· February 2026
arXiv
Parameter-free algorithms for performative regret minimization under decision-dependent distributions
Sungwoo Park, Junyeop Kwon, Byeongnoh Kim, Suhyun Chae, Jeeyong Lee, Dabeen Lee*
Preprint
arXiv
· February 2024
arXiv
2025
A projection-free method for solving convex bilevel optimization problems
Khanh-Hung Giang-Tran, Nam Ho-Nguyen, Dabeen Lee*
Journal
Mathematical Programming
· 213 (2025) 473–516
arXiv
Honorable Mention, INFORMS Undergraduate Operations Research Prize, 2024 INFORMS
From coordinate subspaces over finite fields to ideal multipartite uniform clutters
Ahmad Abdi, Dabeen Lee* (α–β)
Journal
Mathematical Programming
· 213 (2025) 823–861
arXiv
Improved regret bound for safe reinforcement learning via tighter cost pessimism reward optimism
Kihyun Yu, Duksang Lee, William Overman, Dabeen Lee*
Journal
Reinforcement Learning Journal
· 6 (2025) 493–546
paper
Conference
RLC 2025
· Reinforcement Learning Conference
An optimistic algorithm for online CMDPs with anytime adversarial constraints
Jiahui Zhu, Kihyun Yu, Dabeen Lee, Xin Liu, Honghao Wei
Conference
ICML 2025
· International Conference on Machine Learning
arXiv
Reinforcement learning for infinite-horizon average-reward linear MDPs via approximation by discounted-reward MDPs
Kihyuk Hong, Woojin Chae, Yufan Zhang, Dabeen Lee, Ambuj Tewari
Conference
AISTATS 2025
· International Conference on Artificial Intelligence and Statistics
paper
Learning infinite-horizon average-reward linear mixture MDPs of bounded span
Woojin Chae, Kihyuk Hong, Yufan Zhang, Ambuj Tewari, Dabeen Lee*
Conference
AISTATS 2025
· International Conference on Artificial Intelligence and Statistics
paper
Infinite-horizon reinforcement learning with multinomial logit function approximation
Jaehyun Park, Junyeop Kwon, Dabeen Lee*
Conference
AISTATS 2025
· International Conference on Artificial Intelligence and Statistics
paper
Conic mixed-binary sets: convex hull characterizations and applications
Fatma Kılınç-Karzan, Simge Küçükyavuz, Dabeen Lee*, Soroosh Shafieezadeh-Abadeh (α–β)
Journal
Operations Research
· 73(1) (2025) 251–269
arXiv
2022
Distributionally robust chance-constrained programs with right-hand side uncertainty under Wasserstein ambiguity
Nam Ho-Nguyen, Fatma Kılınç-Karzan, Simge Küçükyavuz, Dabeen Lee* (α–β)
Journal
Mathematical Programming
· 196 (2022) 641–672
arXiv
Joint chance-constrained programs and the intersection of mixing sets through a submodularity lens
Fatma Kılınç-Karzan, Simge Küçükyavuz, Dabeen Lee* (α–β)
Journal
Mathematical Programming
· 195 (2022) 283–326
arXiv
On a generalization of the Chvátal-Gomory closure
Sanjeeb Dash, Oktay Günlük, Dabeen Lee* (α–β)
Journal
Mathematical Programming
· 192 (2022) 149–175
arXiv
Conference
IPCO 2020
· Integer Programming and Combinatorial Optimization, LNCS 12125 (2020) 117–129
pdf
Idealness of k-wise intersecting families
Ahmad Abdi, Gérard Cornuéjols, Tony Huynh, Dabeen Lee (α–β)
Journal
Mathematical Programming
· 192 (2022) 29–50
arXiverratum
Conference
IPCO 2020
· Integer Programming and Combinatorial Optimization, LNCS 12125 (2020) 1–12
pdf