4 papers
Optimal Posterior E-values with Non-Convex Parameter Sets with Applications to Voting Systems
Adrienne Tuynman, Timothée Mathieu
We are interested in conducting political polls sequentially, so that one can stop acquiring data as soon as possible while safely yielding statistically significant results. Build…
Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning
Adrien Prevost, Timothee Mathieu, Odalric-Ambrym Maillard
We study the non-contextual multi-armed bandit problem in a transfer learning setting: before any pulls, the learner is given N'_k i.i.d. samples from each source distribution nu'_…
Visual tests using several safe confidence intervals
Timothée Mathieu
We propose a new statistical hypothesis testing framework which decides visually, using confidence intervals, whether the means of two samples are equal or if one is larger than th…
AdaStop: adaptive statistical testing for sound comparisons of Deep RL agents
Timothée Mathieu, Riccardo Della Vecchia, Alena Shilova +4
Recently, the scientific community has questioned the statistical reproducibility of many empirical results, especially in the field of machine learning. To contribute to the resol…