Ha Manh Bui
- Ph.D. Student, Johns Hopkins University
- Gmail: "hb dot buimanhha"
Hi! I am a Ph.D. Student in Computer Science at Johns Hopkins University, advised by Angie Liu. Prior to that, I was at VinAI and obtained a B.S.E. in Information Technology from PTIT-Hanoi, under the supervision of Toan Tran and Dinh Phung.
Research Interests [Research Statement]: I want to develop reliable Machine Learning (ML) systems that can support people in high-stakes applications. My research focuses on improving efficiency, uncertainty, and robustness in ML algorithms for sequential decision problems.
Pre-prints
Q-Learning with Shift-Aware Upper Confidence Bound in Reinforcement Learning [PDF]
Calibrated Uncertainty Sampling for Active Learning [PDF, Colab demo]
Publications
Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits [PDF, article, Colab demo, code, BibTex] Ha Manh Bui, Enrique Mallada, Anqi Liu International Conference on Artificial Intelligence and Statistics, 2025
Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts [PDF, article, talk, Colab demo, code, BibTex] Ha Manh Bui, Anqi Liu International Conference on Machine Learning, 2024
Density-Regression: Efficient and Distance-Aware Deep Regressor for Uncertainty Estimation under Distribution Shifts [PDF, article, talk, Colab demo, code, BibTex] Ha Manh Bui, Anqi Liu International Conference on Artificial Intelligence and Statistics, 2024
Benchmark for Uncertainty & Robustness in Self-Supervised Learning [PDF, article, code, BibTex] Ha Manh Bui, Iliana Maifeld-Carucci arXiv pre-print, 2022
Exploiting Domain-Specific Features to Enhance Domain Generalization [PDF, article, talk, code, BibTex] Manh-Ha Bui, Toan Tran, Anh Tran, Dinh Phung Advances in Neural Information Processing Systems, 2021