Data-Driven Priors in the Maximum Entropy on the Mean Method for Linear Inverse Problems
We establish the theoretical framework for implementing the maximumn entropy on the mean (MEM) method for linear inverse problems in the setting of approximate (data-driven) priors. We prove a.s. convergence for empirical means and further develop general estimates for the difference between the MEM solutions with different priors $\mu$ and $\nu$ based upon the epigraphical distance between their respective log-moment generating functions. These estimates allow us to establish a rate of convergence in expectation for empirical means. We illustrate our results with denoising on MNIST and Fashion-MNIST data sets.
Code (1)
Tasks
DenoisingSimilar Papers 제목 키워드 기반
Gaussian Process Regression for Maximum Entropy Distribution
Maximum-Entropy Distributions offer an attractive family of probability densities suitable for moment closure problems. Yet finding the Lagrange multipliers which parametrize these distributions, turns out to be a comput…
Gaussian ProcessesregressionApproximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods
The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family, has been very popular in machine learning due t…
Filtering Additive Measurement Noise with Maximum Entropy in the Mean
The purpose of this note is to show how the method of maximum entropy in the mean (MEM) may be used to improve parametric estimation when the measurements are corrupted by large level of noise. The method is developed in…
Data Driven Computing with Noisy Material Data Sets
We formulate a Data Driven Computing paradigm, termed max-ent Data Driven Computing, that generalizes distance-minimizing Data Driven Computing and is robust with respect to outliers. Robustness is achieved by means of c…
ClusteringStress-Strain RelationLimit of the Maximum Random Permutation Set Entropy
The Random Permutation Set (RPS) is a new type of set proposed recently, which can be regarded as the generalization of evidence theory. To measure the uncertainty of RPS, the entropy of RPS and its corresponding maximum…