IEEE Transactions on Signal Processing · 2021 · 10 citations · 28 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningStatistical LearningBias-variance TradeoffMutual InformationNeural NetworksProbabilistic Machine LearningResampling MethodsResampling TechniquesConditional Mutual InformationK-nearest NeighborsMutual Information EstimationProduct DensitySample Average Approximation
The estimation of mutual information (MI) or conditional mutual information (CMI) from a set of samples is a longstanding problem. A recent line of work in this area has leveraged the approximation power of artificial neural networks and has shown improvements over conventional methods. One important challenge in this new approach is the need to obtain, given the original dataset, a different set where the samples are distributed according to a specific product density function. This is particularly challenging when estimating CMI. In this paper, we introduce a new technique, based on k nearest neighbors (k-NN), to perform the resampling and derive high-confidence concentration bounds for the sample average. Then the technique is employed to train a neural network classifier and the CMI is estimated accordingly. We propose three estimators using this technique and prove their consistency, make a comparison between them and similar approaches in the literature, and experimentally show improvements in estimating the CMI in terms of accuracy and variance of the estimators.
28
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., WhiteH. · Neural Networks · 1989 · 9.4K citations
Alexander Kraskov, Harald Stögbauer, Peter Grassberger · Physical Review E · 2004 · 4.1K citations · Full text