2 papers
cs.LG2026
Limits of spectral learning under noise
Sabin Roman, Ljupco Todorovski, Saso Dzeroski +2
Learning functional relationships from noisy data is a central problem in scientific inference. Spectral methods approximate unknown functions by expanding them in a basis and esti…
gr-qc2026
Black Holes as Non-Abelian Anyon Condensates: Implications for the Information Paradox
Sabin Roman
We propose a black-hole model in which the would-be horizon is replaced by a thin, topologically ordered timelike shell of condensed non-Abelian anyons surrounding a regular, topol…