99 citations · 428 across the 78 of their papers we have counts for
12 papers · 1 filter
Exact Error in Matrix Completion: Approximately Low-Rank Structures and Missing Blocks
Agostino Capponi, Mihailo Stojnic
We study the completion of approximately low rank matrices with entries missing not at random (MNAR). In the context of typical large-dimensional statistical settings, we establish…
Fl RDT based ultimate lowering of the negative spherical perceptron capacity
Mihailo Stojnic
We consider the classical \emph{spherical} perceptrons and study their capacities. The famous zero-threshold case was solved in the sixties of the last century (see, \cite{Wendel62…
\emph{Lifted} RDT based capacity analysis of the 1-hidden layer treelike \emph{sign} perceptrons neural networks
Mihailo Stojnic
We consider the memorization capabilities of multilayered \emph{sign} perceptrons neural networks (SPNNs). A recent rigorous upper-bounding capacity characterization, obtained in \…
Capacity of the treelike sign perceptrons neural networks with one hidden layer -- RDT based upper bounds
Mihailo Stojnic
We study the capacity of \emph{sign} perceptrons neural networks (SPNN) and particularly focus on 1-hidden layer \emph{treelike committee machine} (TCM) architectures. Similarly to…
Binary perceptrons capacity via fully lifted random duality theory
Mihailo Stojnic
We study the statistical capacity of the classical binary perceptrons with general thresholds . After recognizing the connection between the capacity and the bilinearly indexed…
Studying Hopfield models via fully lifted random duality theory
Mihailo Stojnic
Relying on a recent progress made in studying bilinearly indexed (bli) random processes in \cite{Stojnicnflgscompyx23,Stojnicsflgscompyx23}, the main foundational principles of ful…