Hamish Flynn

Hamish Flynn

Auto-generated profile, based on publicly available information

Hamish Flynn

Bosch Center for Artificial Intelligence, Renningen, Germany

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 March 2022 in Data Mining and Knowledge Discovery
Verified
Journal Article
Closed access
PDF file
HFHamish Flynn
Hamish Flynn
DRDavid Reeb
David Reeb
Melih KandemirMelih Kandemir
Melih Kandemir
Jan PetersJan Peters
Jan Peters

18 August 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
HFHamish Flynn
Hamish Flynn
DRDavid Reeb
David Reeb
Melih KandemirMelih Kandemir
Melih Kandemir
Jan PetersJan Peters
Jan Peters
PAC-Bayes has recently re-emerged as an effective theory with which one can derive principled learning algorithms with tight performance guarantees. However, applications of PAC-Bayes to bandit problems are relatively rare, which is a great misfortune. Many decision-making problems in healthcare, finance and natural sciences can be modelled as bandit problems. In many of these applications, principled algorithms with strong performance guarantees would be very much appreciated. This survey provides an overview of PAC-Bayes bounds for bandit problems and an experimental comparison of these bounds. On the one hand, we found that PAC-Bayes bounds are a useful tool for designing offline bandit algorithms with performance guarantees. In our experiments, a PAC-Bayesian offline contextual bandit algorithm was able to learn randomised neural network polices with competitive expected reward and non-vacuous performance guarantees. On the other hand, the PAC-Bayesian online bandit algorithms that we tested had loose cumulative regret bounds. We conclude by discussing some topics for future work on PAC-Bayesian bandit algorithms.

25 September 2025 in Statistics & Probability Letters
Verified
Journal Article
Open access
ECEugenio Clerico
Eugenio Clerico
HFHamish E. Flynn
Hamish E. Flynn
PRPatrick Rebeschini
Patrick Rebeschini