activity
20172022
most citedQuality of Uncertainty Quantification for Bayesian Neural Network Inference

73 citations · 129 across the 5 of their papers we have counts for

collaborators

9 papers

cs.LG2024

Inverse Reinforcement Learning with Multiple Planning Horizons

Jiayu Yao, Weiwei Pan, Finale Doshi-Velez +1

In this work, we study an inverse reinforcement learning (IRL) problem where the experts are planning under a shared reward function but with different, unknown planning horizons.…

cs.LG2022

Deep Semi-supervised Learning with Double-Contrast of Features and Semantics

Quan Feng, Jiayu Yao, Zhison Pan +1

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. Howeve…

stat.ML2022

An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks

Jiayu Yao, Yaniv Yacoby, Beau Coker +2

Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width increases, multiple model properties change simultaneously, and, inference in t…

cs.LG201973 cited

Quality of Uncertainty Quantification for Bayesian Neural Network Inference

Jiayu Yao, Weiwei Pan, Soumya Ghosh +1

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 t…

cs.LG201910 cited

Output-Constrained Bayesian Neural Networks

Wanqian Yang, Lars Lorch, Moritz A. Graule +5

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 fu…

cs.LG2018

Projected BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

Melanie F. Pradier, Weiwei Pan, Jiayu Yao +2

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkabl…