17 citations · 64 across the 23 of their papers we have counts for
24 papers
Spiking Neural Networks with Elephant Reinforcement
Fernando A. Najman, Ioannis Papageorgiou, Sabricia K. Cauanny A. da Silveira
We introduce a finite stochastic spiking-neuron network with Elephant-type memory, in which past firing activity modifies future excitability through a reinforcement-dependent thre…
Elephant Reinforced Galves-Löcherbach Networks
Ioannis Papageorgiou
We introduce an infinite-dimensional Galves--Löcherbach system with bounded Elephant-type reinforced synaptic interactions. The reinforcement mechanism modifies the probabilities o…
Fundamental limits of distributed multiclass classification from simple binary decisions
Ioannis Papageorgiou, Srinivas Nomula, Ayalvadi Ganesh +2
We consider the problem of constructing a -class classifier from the combination of simple binary classifiers -- this is a natural paradigm to construct a sophistica…
A Spectral Approach to Survival Bounds for the Elephant Random Walk
Cristian Favio Coletti, Rafael de Mattos Grisi, Ioannis Papageorgiou
We study a rate-one Poissonization of the one-dimensional elephant random walk killed upon reaching . For every fixed memory parameter , we give a self-contained proo…
Replica Mean Field limits for neural networks with excitatory and inhibitory activity
Ioannis Papageorgiou
We study Replica Mean Field limits for a neural system of infinitely many neurons with both inhibitory and excitatory interactions. As a result we obtain an analytical characterisa…
The Bayesian Context Trees State Space Model for time series modelling and forecasting
Ioannis Papageorgiou, Ioannis Kontoyiannis
A hierarchical Bayesian framework is introduced for developing tree-based mixture models for time series, partly motivated by applications in finance and forecasting. At the top le…
Truly Bayesian Entropy Estimation
Ioannis Papageorgiou, Ioannis Kontoyiannis
Estimating the entropy rate of discrete time series is a challenging problem with important applications in numerous areas including neuroscience, genomics, image processing and na…
Posterior Representations for Bayesian Context Trees: Sampling, Estimation and Convergence
Ioannis Papageorgiou, Ioannis Kontoyiannis
We revisit the Bayesian Context Trees (BCT) modelling framework for discrete time series, which was recently found to be very effective in numerous tasks including model selection,…
Context-tree weighting for real-valued time series: Bayesian inference with hierarchical mixture models
Ioannis Papageorgiou, Ioannis Kontoyiannis
Real-valued time series are ubiquitous in the sciences and engineering. In this work, a general, hierarchical Bayesian modelling framework is developed for building mixture models…
Bayesian Context Trees: Modelling and exact inference for discrete time series
Ioannis Kontoyiannis, Lambros Mertzanis, Athina Panotopoulou +2
We develop a new Bayesian modelling framework for the class of higher-order, variable-memory Markov chains, and introduce an associated collection of methodological tools for exact…
Asymptotic Analysis of the Elephant Random Walk
Cristian F. Coletti, Ioannis Papageorgiou
In this work we study asymptotic properties of a long range memory random walk known as elephant random walk. First we prove recurrence and positive recurrence for the elephant ran…
Interacting systems of infinite spiking neurons with weights beyond uniform summability
Ioannis Papageorgiou
We consider an infinite system of spiking neurons with a drift and both excitatory and inhibitory connections. We study conditions for non-explosiveness and the uniqueness of the i…
The log-Sobolev inequality for spin systems of higher order interactions
Takis Konstantopoulos, Ioannis Papageorgiou
We study the infinite-dimensional log-Sobolev inequality for spin systems on with interactions of power higher than quadratic. We assume that the one site measure wi…
Modified log-Sobolev inequality for a compact PJMP with degenerate jumps
Ioannis Papageorgiou
We study the modified log-Sobolev inequality for a class of pure jump Markov processes that describe the interactions between brain neurons. In particular, we focus on a finite and…
Concentration and Poincaré type inequalities for a degenerate pure jump Markov process
Pierre Hodara, Ioannis Papageorgiou
We study Talagrand concentration and Poincaré type inequalities for unbounded pure jump Markov processes. In particular we focus on processes with degenerate jumps that depend on t…
Poincaré type inequalities for compact degenerate pure jump Markov processes
Pierre Hodara, Ioannis Papageorgiou
We aim in proving Poincaré inequalities for a class of pure jump Markov processes inspired by the model introduced in \cite{G-L} by Galves and Löcherbach to describe the behaviour…
The log-Sobolev inequality with quadratic interactions
Ioannis Papageorgiou
We assume one site measures without a boundary that satisfy a log-Sobolev inequality. We prove that if these measures are perturbed with quadratic interactions, the…
Cutoff for random walks on graphs with bottlenecks
Ioannis Papageorgiou
We examine the mixing time for random walks on graphs. In particular we are interested on investigating graphs with bottlenecks. Furthermore, the cutoff phenomenon is examined.
Log-Sobolev inequalities for infinite-dimensional Gibbs measures with non-quadratic interactions
James Inglis, Ioannis Papageorgiou
We focus on the log-Sobolev inequality for spin systems on the lattice with interactions of higher order than quadratic. We show that if the one-dimensional single-site measure wit…
A note on the Modified Log-Sobolev inequality
Ioannis Papageorgiou
A criterion is presented for the Modified Logarithmic Sobolev inequality on metric measure spaces. The criterion based on U-bound inequalities introduced by Hebisch and Zegarlinski…
Concentration inequalities for Gibbs measures
Ioannis Papageorgiou
We are interested in Sobolev type inequalities and their relationship with concentration properties on higher dimensions. We consider unbounded spin systems on the d-dimensional la…
Logarithmic Sobolev inequalities for infinite dimensional Hörmander type generators on the Heisenberg group
James Inglis, Ioannis Papageorgiou
The Heisenberg group is one of the simplest sub-Riemannian settings in which we can define non-elliptic Hörmander type generators. We can then consider coercive inequalities associ…
The Logarithmic Sobolev Inequality for Gibbs measures on infinite product of Heisenberg groups
Ioannis Papageorgiou
We are interested in the Logarithmic Sobolev inequality for probability measures on the infinite product of Heisenberg groups. We assume that the one site boundary free measure…
The Logarithmic Sobolev Inequality in Infinite dimensions for Unbounded Spin Systems on the Lattice with non Quadratic Interactions
Ioannis Papageorgiou
We are interested in the Logarithmic Sobolev Inequality for the infinite volume Gibbs measure with no quadratic interactions. We consider unbounded spin systems on the one dimensio…