2 code implementations • 3 Apr 2024 • Philipp Hager, Romain Deffayet, Jean-Michel Renders, Onno Zoeter, Maarten de Rijke
Our experiments reveal that gains in click prediction do not necessarily translate to enhanced ranking performance on expert relevance annotations, implying that conclusions strongly depend on how success is measured in this benchmark.
no code implementations • 1 Mar 2024 • Philip Boeken, Onno Zoeter, Joris M. Mooij
In this work, we propose to model the deployment of a DSS as causal domain shift and provide novel cross-domain identification results for the conditional expectation $E[Y | X]$, allowing for pre- and post-hoc assessment of the deployment of the DSS, and for retraining of a model that assesses the risk under a baseline policy where the DSS is not deployed.
no code implementations • 19 Feb 2024 • Davide Mambelli, Stephan Bongers, Onno Zoeter, Matthijs T. J. Spaan, Frans A. Oliehoek
A well-established off-policy objective is the excursion objective.
no code implementations • 12 Jan 2024 • Leihao Chen, Onno Zoeter, Joris M. Mooij
Selection bias is ubiquitous in real-world data, and can lead to misleading results if not dealt with properly.
no code implementations • 13 Apr 2023 • Jiale Chen, Jason Hartline, Onno Zoeter
In a randomized exam, each student is asked a small number of random questions from a large question bank.
1 code implementation • 29 Mar 2023 • Philip Boeken, Noud de Kroon, Mathijs de Jong, Joris M. Mooij, Onno Zoeter
We conclude that repeated regression can appropriately correct for bias, and can have considerable advantage over weighted regression, especially when extrapolating to regions of the feature space where response is never observed.
no code implementations • 27 Jun 2014 • Shweta Jain, Sujit Gujar, Satyanath Bhat, Onno Zoeter, Y. Narahari
First, we propose a framework, Assured Accuracy Bandit (AAB), which leads to an MAB algorithm, Constrained Confidence Bound for a Non Strategic setting (CCB-NS).
no code implementations • NeurIPS 2011 • Shengbo Guo, Onno Zoeter, Cédric Archambeau
We propose a new sparse Bayesian model for multi-task regression and classification.