430 citations · 830 across the 11 of their papers we have counts for
8 papers · 1 filter
What Are Bayesian Neural Network Posteriors Really Like?
Pavel Izmailov, Sharad Vikram, Matthew D. Hoffman +1
The posterior over Bayesian neural network (BNN) parameters is extremely high-dimensional and non-convex. For computational reasons, researchers approximate this posterior using in…
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan +37
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Tom Le Paine, Caglar Gulcehre, Bobak Shahriari +11
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial…
Autoconj: Recognizing and Exploiting Conjugacy Without a Domain-Specific Language
Matthew D. Hoffman, Matthew J. Johnson, Dustin Tran
Deriving conditional and marginal distributions using conjugacy relationships can be time consuming and error prone. In this paper, we propose a strategy for automating such deriva…
The LORACs prior for VAEs: Letting the Trees Speak for the Data
Sharad Vikram, Matthew D. Hoffman, Matthew J. Johnson
In variational autoencoders, the prior on the latent codes is often treated as an afterthought, but the prior shapes the kind of latent representation that the model learns. If…
Music Transformer
Cheng-Zhi Anna Huang, Ashish Vaswani, Jakob Uszkoreit +7
Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such…