Home

Hi! I'm Romain, a final year Ph.D. student in Computer Science & Engineering at the University of Washington working with Kevin Jamieson. My passion lies in improving the reliability of machine learning algorithms. I'm dedicated to developing trustworthy machine learning solutions for problems with limited and expensive data, by leveraging sequential decision making and efficient data collection.  My research has contributed to advancements in addressing these critical issues by tackling challenges related to ensuring the robustness, safety, and fairness of models within both statistical and interactive learning frameworks, such as active learning, bandits and online learning.

Before that, I worked with Zaid Harchaoui and Maryam Fazel on imitation learning and safe statistical learning for applications in robotics. I completed a master degree at ENS Paris-Saclay in Mathematics Applied to Vision and Learning (MVA) and a master degree at Mines Paristech in Statistics and Probabilities. I also studied applications of operators adapted wavelets to image processing with Houman Owhadi during an exchange program with the CMS department of Caltech.

Publications: (Google Scholar profile)

A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity, Zhihan Xiong*, Romain Camilleri*, Maryam Fazel, Lalit Jain, Kevin Jamieson,  AISTATS 2024, CODE@MIT 2023, arxiv 

Active Learning with Safety Constraints, Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern, Lalit Jain, Kevin Jamieson, NeurIPS 2022, arxiv 

Nearly Optimal Algorithms for Level Set Estimation, Blake Mason, Romain Camilleri, Subhojyoti Mukherjee, Kevin Jamieson, Robert Nowak, Lalit Jain, AISTATS 2022, arxiv

Selective Sampling for Online Best-Arm Identification, Romain Camilleri*, Zhihan Xiong*, Maryam Fazel, Lalit Jain, Kevin Jamieson, NeurIPS 2021, arxiv 

High-Dimensional Experimental Design and Kernel Bandits, Romain Camilleri, Julian Katz-Samuels, Kevin Jamieson, ICML 2021, long presentation (3% acceptance rate), arxiv 

Internship experience:

Summer 2022: research in explainability of recommender systems with Moises Goldszmidt at Apple AI/ML 

Summer 2020: research in hyperparameter optimization with Zohar Karnin at Amazon AWS

Contact:

Email: camilr at cs dot washington dot edu