DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Designby Samuel Garcin, James Doran, Shangmin…
Early prediction of onset of sepsis in Clinical Settingby Fahim Mohammad, Lakshmi Arunachalam, Samanway Sadhu,…
Attention Meets Post-hoc Interpretability: A Mathematical Perspectiveby Gianluigi Lopardo, Frederic Precioso, Damien GarreauFirst submitted to…
Partially Stochastic Infinitely Deep Bayesian Neural Networksby Sergio Calvo-Ordonez, Matthieu Meunier, Francesco Piatti, Yuantao ShiFirst…
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspectiveby Wu Lin, Felix…
How Does Unlabeled Data Provably Help Out-of-Distribution Detection?by Xuefeng Du, Zhen Fang, Ilias Diakonikolas, Yixuan…
Neural networks for abstraction and reasoning: Towards broad generalization in machinesby Mikel Bober-Irizar, Soumya BanerjeeFirst…
Evaluating the Factuality of Zero-shot Summarizers Across Varied Domainsby Sanjana Ramprasad, Kundan Krishna, Zachary C…
Deep Reinforcement Learning for Picker Routing Problem in Warehousingby George Dunn, Hadi Charkhgard, Ali Eshragh,…
Consistent Validation for Predictive Methods in Spatial Settingsby David R. Burt, Yunyi Shen, Tamara BroderickFirst…