7 papers
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
Obed Junias, Maria Leonor Pacheco
Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms correctly. We st…
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 Poincaré Inequality and Exponential Decay for the Elephant Random Walk
Cristian Favio Coletti, Rafael de Mattos Grisi, Ioannis Papageorgiou
We study the long-time behaviour of a coninuous time one-dimensional elephant random walk with an absorbing boundary. By analyzing the associated evolution equation, we identify a…
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…
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…