Home page

Publications

Linear bandits with non-i.i.d. noise
Baptiste Abélès, Eugenio Clerico, Hamish Flynn, Gergely Neu;
Preprint.

Confidence sequences for generalized linear models via regret analysis
Eugenio Clerico, Hamish Flynn, Wojciech Kotłowski, Gergely Neu;
Preprint.

Relative information gain and Gaussian process regression
Hamish Flynn;
ALT, 2026.

Sparse nonparametric contextual bandits
Hamish Flynn, Julia Olkhovskaya, Paul Rognon-Vael;
ALT, 2026.

Sparse optimistic information directed sampling
Ludovic Schwartz, Hamish Flynn, Gergely Neu;
NeurIPS, 2025.

Uniform mean estimation for monotonic processes
Eugenio Clerico, Hamish Flynn, Patrick Rebeschini;
Statistics and Probability Letters, 2025.

Tighter confidence bounds for sequential kernel regression
Hamish Flynn, David Reeb;
AISTATS, 2025.

Improved algorithms for stochastic linear bandits using tail bounds for martingale mixtures
Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters;
NeurIPS, 2023.

PAC-Bayes bounds for bandit problems: a survey and experimental comparison
Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters;
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.

PAC-Bayesian lifelong learning for multi-armed bandits
Hamish Flynn, David Reeb, Melih Kandemir, Jan Peters;
Data Mining and Knowledge Discovery, 2022.