99 citations · 428 across the 78 of their papers we have counts for
8 papers · 2 filters
Deep ReLU networks -- injectivity capacity upper bounds
Mihailo Stojnic
We study deep ReLU feed forward neural networks (NN) and their injectivity abilities. The main focus is on \emph{precisely} determining the so-called injectivity capacity. For any…
Injectivity capacity of ReLU gates
Mihailo Stojnic
We consider the injectivity property of the ReLU networks layers. Determining the ReLU injectivity capacity (ratio of the number of layer's inputs and outputs) is established as is…
Theoretical limits of descending sparse-regression ML algorithms
Mihailo Stojnic
We study the theoretical limits of the (quasi) norm based optimization algorithms when employed for solving classical compressed sensing or sparse regression problems. Con…
Precise analysis of ridge interpolators under heavy correlations -- a Random Duality Theory view
Mihailo Stojnic
We consider fully row/column-correlated linear regression models and study several classical estimators (including minimum norm interpolators (GLS), ordinary least squares (LS), an…
Ridge interpolators in correlated factor regression models -- exact risk analysis
Mihailo Stojnic
We consider correlated \emph{factor} regression models (FRM) and analyze the performance of classical ridge interpolators. Utilizing powerful \emph{Random Duality Theory} (RDT) mat…
Capacity of the Hebbian-Hopfield network associative memory
Mihailo Stojnic
In \cite{Hop82}, Hopfield introduced a \emph{Hebbian} learning rule based neural network model and suggested how it can efficiently operate as an associative memory. Studying rando…