Bayesian Learning
The Memory Perturbation Equation: Understanding Model's Sensitivity to Data Peter Nickl
Understanding model's sensitivity to its training data is crucial but can also be challenging and costly, especially during training. To simplify such issues, we present the Memory-Perturbation Equation (MPE) which relates model's sensitivity to perturbation in its training data.
PAC-Bayes under potentially heavy tails
WederivePAC-Bayesian learning guarantees forheavy-tailed losses, andobtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds atlogarithmic confidence. Ourcoretechnique itselfmakesuseofPAC-Bayesian inequalities in order to derive a robust risk estimator, which by design is easy to compute.
Undirected Probabilistic Model for Tensor Decomposition
Tensor decompositions (TDs) serve as a powerful tool for analyzing multiway data.
Online sampling from log-concave distributions
Holden Lee, Oren Mangoubi, Nisheeth Vishnoi
Neural Information Processing Systems http://nips.cc/
An Adaptive Empirical Bayesian Method for Sparse Deep Learning
Wei Deng, Xiao Zhang, Faming Liang, Guang Lin
Neural Information Processing Systems http://nips.cc/