no code implementations • 6 Mar 2024 • Mihailo Stojnic
We consider \emph{random linear programs} (rlps) as a subclass of \emph{random optimization problems} (rops) and study their typical behavior.
no code implementations • 4 Mar 2024 • 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.
no code implementations • 8 Feb 2024 • Mihailo Stojnic
We obtain explicit, closed form, capacity characterizations for a very generic class of the hidden layer activations.
no code implementations • 8 Feb 2024 • Mihailo Stojnic
In more concrete terms, for each of these activations, we obtain both the RDT and pl RDT based memory capacities upper bound characterization for \emph{any} given (even) number of the hidden layer neurons, $d$.
no code implementations • 27 Dec 2023 • Mihailo Stojnic
We here first show that the \emph{negative spherical perceptrons} can be fitted into the frame of the fl RDT and then employ the whole fl RDT machinery to characterize the capacity.
no code implementations • 13 Dec 2023 • Mihailo Stojnic
Moreover, for particular \emph{treelike committee machines} (TCM) architectures with $d\leq 5$ neurons in the hidden layer, \cite{Stojnictcmspnncaprdt23} made a very first mathematically rigorous progress in over 30 years by lowering the previously best known capacity bounds of \cite{MitchDurb89}.
no code implementations • 13 Dec 2023 • 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.
no code implementations • 29 Nov 2023 • Mihailo Stojnic
In particular, we rely on \emph{fully lifted} random duality theory (fl RDT) established in \cite{Stojnicflrdt23} to create a general framework for studying the perceptrons' capacities.
no code implementations • 2 Jan 2023 • Agostino Capponi, Mihailo Stojnic
In this paper, we revisit and further explore a mathematically rigorous connection between Causal inference (C-inf) and the Low-rank recovery (LRR) established in [10].
no code implementations • 2 Jan 2023 • Agostino Capponi, Mihailo Stojnic
In this paper we establish a mathematically rigorous connection between Causal inference (C-inf) and the low-rank recovery (LRR).
no code implementations • 17 Jun 2013 • Mihailo Stojnic
An introductory statistical mechanics treatment of such perceptrons was given in \cite{GutSte90}.
no code implementations • 17 Jun 2013 • Mihailo Stojnic
In Gardner's original work the statistical mechanics predictions in this directions were presented sa well.
no code implementations • 29 Mar 2013 • Mihailo Stojnic
In our recent work \cite{StojnicGenSocp10} we established an alternative framework that can be used for statistical performance analysis of the SOCP algorithms.