Bayesian Inference
Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift
We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures.
Variational Gaussian Processes For Linear Inverse Problems
By now Bayesian methods are routinely used in practice for solving inverse problems.
Amortized Inference Regularization
Rui Shu, Hung H. Bui, Shengjia Zhao, Mykel J. Kochenderfer, Stefano Ermon
Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate.
Residual Flows for Invertible Generative Modeling
Tian Qi Chen, Jens Behrmann, David K. Duvenaud, Joern-Henrik Jacobsen
Neural Information Processing Systems http://nips.cc/
Variational Bayesian Decision-making for Continuous Utilities
Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami
Bayesian decision theory outlines arigorous framework for making optimal decisions based on maximizing expected utility over a model posterior.
daff682411a64632e083b9d6665b1d30-Supplemental-Conference.pdf
Many high-dimensional statistical inference problems are believed to possess inherent computational hardness. Various frameworks have been proposed to give rigorous evidence for such hardness, including lower bounds against restricted models of computation (such as low-degree functions), as well as methods rooted in statistical physics that are based on free energy landscapes. This paper aims to make a rigorousconnectionbetween the seeminglydifferent low-degreeand free-energybased approaches. We define a free-energybasedcriterionfor hardnessand formallyconnectit to the well-establishednotionof low-degree hardness for a broad class of statistical problems, namely all Gaussian additive models and certain models with a sparse planted signal.
