Research

Mathematics of statistical sequential decision-making: concentration, risk-awareness and modelling in stochastic bandits, with applications to bariatric surgery

PhD thesis.

Development and validation of an interpretable machine learning-based calculator for predicting 5-year weight trajectories after bariatric surgery: a multinational retrospective cohort SOPHIA study (The Lancet Digital Health)

An interpretable, tree-based prediction model for long term weight loss after bariatric surgery.

Impact of robotic assistance on complications in bariatric surgery at expert laparoscopic surgery centers. A retrospective comparative study with propensity score (Annals of Surgery)

Does robotic assistance help bariatric surgery? A causal inference study.

Risk-aware linear bandits with convex loss (EWRL 2022, AISTATS 2023)

Linear bandits with a twist.

Bregman deviations of generic exponential families (COLT 2023)

Time-uniform concentration for a vast class of parametric distributions.

From optimality to robustness: Dirichlet sampling strategies in stochastic bandits (NeurIPS 2021)

State-of-the-art randomised bandit algorithm with guarantees under weak assumptions.