The Population Posterior and Bayesian Modeling on Streams

35 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Optimal Continual Learning has Perfect Memory and is NP-hard (2020, background): “Similarly, the contributions to sequential and streaming learning made by Honkela & Valpola (2003), Broderick et al. (2013) or McInerney et al. (2015) are geared towards streaming settings in which the differences in observations a r X i v : 2006 .”
Lifelong Generative Modeling (2017, methodology): “Variational methods have been adapted for a streaming setting, e.g: Streaming Variational Bayes Broderick et al. (2013), Streaming Variational Mixture models Tank et al. (2015), and the Population Posterior McInerney et al. (2015).”
Advances in Variational Inference (2017, background): “this end, [117] introduces the concept of the population posterior which depends on the unknown size of the dataset.”
Variational Tempering (2014, unknown): “We 1 Even higher likelihoods were obtained using the learned temperature distributions for prediction, implying a beneﬁcial role for the tempered model in dealing with outliers and model mismatch, similar to McInerney et al. (2015).”
Continual Learning with Bayesian Neural Networks for Non-Stationary Data (2020, background): “For example McInerney et al. (2015) treat the learning dynamics of their model as a non-stationary process that allows for adaptation.”