Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Yao, Jiayu"'
Offline reinforcement learning learns an effective policy on offline datasets without online interaction, and it attracts persistent research attention due to its potential of practical application. However, extrapolation error generated by distribut
Externí odkaz:
http://arxiv.org/abs/2301.01298
In recent years, the field of intelligent transportation systems (ITS) has achieved remarkable success, which is mainly due to the large amount of available annotation data. However, obtaining these annotated data has to afford expensive costs in rea
Externí odkaz:
http://arxiv.org/abs/2211.15671
Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width increases, multiple model properties change simultaneously, and, inference in the finite-width case is intractable. In this work, we empirically comp
Externí odkaz:
http://arxiv.org/abs/2211.09184
Autor:
Penrod, Mark, Termotto, Harrison, Reddy, Varshini, Yao, Jiayu, Doshi-Velez, Finale, Pan, Weiwei
Publikováno v:
International Conference on Machine Learning. PMLR 162 (2022)
For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from litera
Externí odkaz:
http://arxiv.org/abs/2208.01705
We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes. Our goal is to make minimal changes while gaining as much benefit as possible. We define a minimal change as having a
Externí odkaz:
http://arxiv.org/abs/2207.06269
Self-supervised learning (SSL), as a newly emerging unsupervised representation learning paradigm, generally follows a two-stage learning pipeline: 1) learning invariant and discriminative representations with auto-annotation pretext(s), then 2) tran
Externí odkaz:
http://arxiv.org/abs/2204.05248
Publikováno v:
Proceedings of the 3rd Machine Learning for Health Symposium, PMLR 225:323-339, 2023
Reinforcement learning (RL) is an effective framework for solving sequential decision-making tasks. However, applying RL methods in medical care settings is challenging in part due to heterogeneity in treatment response among patients. Some patients
Externí odkaz:
http://arxiv.org/abs/2110.02879
Contextual bandits often provide simple and effective personalization in decision making problems, making them popular tools to deliver personalized interventions in mobile health as well as other health applications. However, when bandits are deploy
Externí odkaz:
http://arxiv.org/abs/2004.06230
Bayesian Neural Networks (BNNs) place priors over the parameters in a neural network. Inference in BNNs, however, is difficult; all inference methods for BNNs are approximate. In this work, we empirically compare the quality of predictive uncertainty
Externí odkaz:
http://arxiv.org/abs/1906.09686
Autor:
Yang, Wanqian, Lorch, Lars, Graule, Moritz A., Srinivasan, Srivatsan, Suresh, Anirudh, Yao, Jiayu, Pradier, Melanie F., Doshi-Velez, Finale
Bayesian neural network (BNN) priors are defined in parameter space, making it hard to encode prior knowledge expressed in function space. We formulate a prior that incorporates functional constraints about what the output can or cannot be in regions
Externí odkaz:
http://arxiv.org/abs/1905.06287