Out of all the good things coming out of this paper, here is what I note: The Great Convergence continues and we also find phase transitions. Also even though reconstruction is noisy, it is still perceptually ok because humans have been dealing with all sorts of imprecisions in their vision systems.
The spiked matrix model with generative priors by Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová
Using a low-dimensional parametrization of signals is a generic and powerful way to enhance performance in signal processing and statistical inference. A very popular and widely explored type of dimensionality reduction is sparsity; another type is generative modelling of signal distributions. Generative models based on neural networks, such as GANs or variational auto-encoders, are particularly performant and are gaining on applicability. In this paper we study spiked matrix models, where a low-rank matrix is observed through a noisy channel. This problem with sparse structure of the spikes has attracted broad attention in the past literature. Here, we replace the sparsity assumption by generative modelling, and investigate the consequences on statistical and algorithmic properties. We analyze the Bayes-optimal performance under specific generative models for the spike. In contrast with the sparsity assumption, we do not observe regions of parameters where statistical performance is superior to the best known algorithmic performance. We show that in the analyzed cases the approximate message passing algorithm is able to reach optimal performance. We also design enhanced spectral algorithms and analyze their performance and thresholds using random matrix theory, showing their superiority to the classical principal component analysis. We complement our theoretical results by illustrating the performance of the spectral algorithms when the spikes come from real datasets.
An implementation of the results can be found here: https://github.com/sphinxteam/StructuredPrior_demo
h/t Lenka's tweet.
Liked this entry ? subscribe to Nuit Blanche's feed, there's more where that came from. You can also subscribe to Nuit Blanche by Email.
Paris Machine Learning: Meetup.com||@Archives||LinkedIn||Facebook|| @ParisMLGroup< br/> About LightOn: Newsletter ||@LightOnIO|| on LinkedIn || on CrunchBase || our Blog
About myself: LightOn || Google Scholar || LinkedIn ||@IgorCarron ||Homepage||ArXiv