Timezone: »

 
Oral
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
Soumya Ghosh · Jiayu Yao · Finale Doshi-Velez

Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A4
in Deep Learning (Bayesian) 3 »

Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection---even choosing the number of nodes---remains an open question. Recent work has proposed the use of a horseshoe prior over node pre-activations of a Bayesian neural network, which effectively turns off nodes that do not help explain the data. In this work, we propose several modeling and inference advances that consistently improve the compactness of the model learned while maintaining predictive performance, especially in smaller-sample settings including reinforcement learning.

[ PDF] 

Author Information

Soumya Ghosh (IBM Research)
Jiayu Yao (Harvard University)
Finale Doshi-Velez (Harvard University)
Finale Doshi-Velez

Finale Doshi-Velez is a Gordon McKay Professor in Computer Science at the Harvard Paulson School of Engineering and Applied Sciences. She completed her MSc from the University of Cambridge as a Marshall Scholar, her PhD from MIT, and her postdoc at Harvard Medical School. Her interests lie at the intersection of machine learning, healthcare, and interpretability. Selected Additional Shinies: BECA recipient, AFOSR YIP and NSF CAREER recipient; Sloan Fellow; IEEE AI Top 10 to Watch

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors