3 papers
math.LO2026
The tolerant learning hierarchy for c.e. sets
Vittorio Cipriani, Martin Ritter, Luca San Mauro
Learning from positive data models a scenario in which a learner receives longer and longer initial segments of an enumeration of an unknown set and repeatedly outputs a conjecture…
cs.LG2025
On statistical learning of graphs
Vittorio Cipriani, Valentino Delle Rose, Luca San Mauro +1
We study PAC and online learnability of hypothesis classes formed by copies of a countably infinite graph G, where each copy is induced by permuting G's vertices. This corresponds…
math.LO2025
On the learning power of Friedman-Stanley jumps
Vittorio Cipriani, Alberto Marcone, Luca San Mauro
Recently, a surprising connection between algorithmic learning of algebraic structures and descriptive set theory has emerged. Following this line of research, we define the learni…