Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022
Quasi-orthogonality and intrinsic dimensions as measures of learning and generalisation
Qinghua Zhou, Alexander N. Gorban, Evgeny M. Mirkes +3
Finding best architectures of learning machines, such as deep neural networks, is a well-known technical and theoretical challenge. Recent work by Mellor et al (2021) showed that t…
cs.LG2020
Local intrinsic dimensionality estimators based on concentration of measure
Jonathan Bac, Andrei Zinovyev
Intrinsic dimensionality (ID) is one of the most fundamental characteristics of multi-dimensional data point clouds. Knowing ID is crucial to choose the appropriate machine learnin…
cs.LG2019
Estimating the effective dimension of large biological datasets using Fisher separability analysis
Luca Albergante, Jonathan Bac, Andrei Zinovyev
Modern large-scale datasets are frequently said to be high-dimensional. However, their data point clouds frequently possess structures, significantly decreasing their intrinsic dim…