Newton Mwai

About Me

I am a finalist Computer Science and Engineering PhD student in the Healthy AI Lab at Chalmers University of Technology and the Wallenberg AI, Autonomous Systems and Software Program (WASP) Sweden. I am fortunate to be advised by Fredrik D. Johansson. My research focuses on designing interactive sequential learning algorithms for personalization, particularly in healthcare settings. I develop sample-efficient bandit algorithms that leverage historical data and incorporate real-world constraints to improve treatment personalization. My work is also applicable to broader interactive personalization tasks, such as content recommendation in internet media.

I hold a Master's degree in Electrical and Computer Engineering from Carnegie Mellon University and dual Bachelor's degrees in Electrical and Electronics Engineering and Telecommunication and Information Engineering from Dedan Kimathi University of Technology.

Recent News

• September 2025: Expected completion of PhD in Computer Science & Engineering at Chalmers University of Technology. Seeking industry opportunities in machine learning.
• July 2025: Upcoming publication to appear in International Conference on Machine Learning (ICML) 2025, on Prediction models that learn to avoid missing values.
• March 2025: Gave a talk at IBM Research in Nairobi, Kenya: Improving treatment personalization with structures in sequential decision making.
• January 2025: Gave a talk at Research Institutes of Sweden (RISE) Learning Machines Seminar: Improving treatment personalization with structures in sequential decision making [Youtube]
• 2024: Presented at ICML 2024 workshop on aligning reinforcement learning experimentalists and theorists: Batched fixed-confidence pure exploration for bandits with switching constraints.
• 2023: Awarded Licentiate of Philosophy in Computer Science & Engineering from Chalmers University of Technology.

Publications

• 2025: Newton Mwai, Emil Carlsson, and Fredrik D Johansson. Latent Preference Bandits. In submission, under review, 2025. [PDF]
• 2025: Newton Mwai, Milad Malekipirbazari, and Fredrik D Johansson. Understanding exploration in bandits with switching constraints: A batched approach in fixed-confidence pure exploration. In submission, under review, 2025. [PDF]
• 2025: Balcıoğlu Ahmet Zahid, Newton Mwai, Emil Carlsson, and Fredrik D Johansson. Identifiable Latent Bandits: Leveraging observational data for personalized decision-making In submission, under review, 2025. [PDF]
• 2025: Stempfle Lena, Anton Matsson, Newton Mwai, and Fredrik D Johansson. Prediction models that learn to avoid missing values. In International Conference on Machine Learning (ICML), 2025. [URL]
• 2025: Orrelid Christoffer Ivarsson, Oscar Rosberg, Sophia Weiner, Fredrik D Johansson, Johan Gobom, Henrik Zetterberg, Newton Mwai, and Lena Stempfle. Applying machine learning to high-dimensional proteomics datasets for the identification of Alzheimer's disease biomarkers. Fluids and Barriers of the CNS, volume 22, page 23. Springer, 2025. [URL]
• 2024: Newton Mwai, Milad Malekipirbazari, and Fredrik D Johansson. Batched fixed-confidence pure exploration for bandits with switching constraints. In ICML 2024 workshop: aligning reinforcement learning experimentalists and theorists, 2024. [URL]
• 2023: Newton Mwai, Emil Carlsson, and Fredrik D Johansson. Fast treatment personalization with latent bandits in fixed-confidence pure exploration. Transactions on Machine Learning Research, 2023. [URL]
• 2023: Newton Mwai. Improved Sequential Decision-Making with Structural Priors: Enhanced Treatment Personalization with Historical Data. Licentiate thesis, Chalmers University of Technology, Sweden, 2023. [URL]
• 2022: Newton Mwai and Fredrik D Johansson. ADCB: An Alzheimer's disease simulator for benchmarking observational estimators of causal effects. In Conference on Health, Inference, and Learning, pages 103-118. PMLR, 2022. [URL]
• 2020: Newton Mwai, Timothy Odonga, Celia Cintas, Noel CF Codella, Rameswar Panda, Prasanna Sattigeri, and Kush R Varshney. Fairness of classifiers across skin tones in dermatology. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 320-329. Springer, 2020. [URL]
• 2019: Newton Mwai, Timothy Odonga, Celia Cintas, Noel CF Codella, Rameswar Panda, Prasanna Sattigeri, and Kush R Varshney. Estimating skin tone and effects on classification performance in dermatology datasets. In NeurIPS Workshop on Fair ML for Health, 2019. [URL]