no code implementations • 6 Feb 2024 • Mert Ketenci, Iñigo Urteaga, Victor Alfonso Rodriguez, Noémie Elhadad, Adler Perotte
Shapley values have emerged as a foundational tool in machine learning (ML) for elucidating model decision-making processes.
no code implementations • 2 Nov 2023 • Mert Ketenci, Adler Perotte, Noémie Elhadad, Iñigo Urteaga
We present a novel stochastic variational Gaussian process ($\mathcal{GP}$) inference method, based on a posterior over a learnable set of weighted pseudo input-output points (coresets).
1 code implementation • 24 Mar 2022 • Iñigo Urteaga, Moulay-Zaïdane Draïdia, Tomer Lancewicki, Shahram Khadivi
We propose a multi-armed bandit framework for the sequential selection of TLM pre-training hyperparameters, aimed at optimizing language model performance, in a resource efficient manner.
1 code implementation • 24 Feb 2021 • Kathy Li, Iñigo Urteaga, Amanda Shea, Virginia J. Vitzthum, Chris H. Wiggins, Noémie Elhadad
Our model offers several advantages: 1) accounting explicitly for self-tracking artifacts yields better prediction accuracy as likelihood of skipping increases; 2) because it is a generative model, predictions can be updated online as a given cycle evolves, and we can gain interpretable insight into how these predictions change over time; and 3) its hierarchical nature enables modeling of an individual's cycle length history while incorporating population-level information.
1 code implementation • 27 Aug 2019 • Iñigo Urteaga, Tristan Bertin, Theresa M. Hardy, David J. Albers, Noémie Elhadad
We present an end-to-end statistical framework for personalized, accurate, and minimally invasive modeling of female reproductive hormonal patterns.
no code implementations • 6 Nov 2018 • Iñigo Urteaga, Mollie McKillop, Sharon Lipsky-Gorman, Noémie Elhadad
We investigate the use of self-tracking data and unsupervised mixed-membership models to phenotype endometriosis.
1 code implementation • 8 Aug 2018 • Iñigo Urteaga, Chris H. Wiggins
The proposed Bayesian nonparametric mixture model Thompson sampling sequentially learns the reward model that best approximates the true, yet unknown, per-arm reward distribution, achieving successful regret performance.
1 code implementation • 8 Aug 2018 • Iñigo Urteaga, Chris H. Wiggins
We here utilize SMC for estimation of the statistics Bayesian MAB agents compute, and devise flexible policies that can address a rich class of bandit problems: i. e., MABs with nonlinear, stateless- and context-dependent reward distributions that evolve over time.
1 code implementation • 30 Nov 2017 • Iñigo Urteaga, David J. Albers, Marija Vlajic Wheeler, Anna Druet, Hans Raffauf, Noémie Elhadad
The motivation for this work is to model the hormonal cycle and predict its phases in time, both for healthy individuals and for those with disorders of the reproductive system.
1 code implementation • 10 Sep 2017 • Iñigo Urteaga, Chris H. Wiggins
One general class of algorithms for optimizing interactions with the world, while simultaneously learning how the world operates, is the multi-armed bandit setting and, in particular, the contextual bandit case.
1 code implementation • 10 Sep 2017 • Iñigo Urteaga, Chris H. Wiggins
Reinforcement learning studies how to balance exploration and exploitation in real-world systems, optimizing interactions with the world while simultaneously learning how the world operates.