output
20142025
most citedGeomstats: A Python Package for Riemannian Geometry in Machine Learning

96 citations

Showing 2023Show all

6 papers · 1 filter

cs.DC202332 cited

Distributed convergence detection based on global residual error under asynchronous iterations

Frédéric Magoulès, Guillaume Gbikpi-Benissan

Convergence of classical parallel iterations is detected by performing a reduction operation at each iteration in order to compute a residual error relative to a potential solution…

cs.CL2023

Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models

Pierre Colombo, Victor Pellegrain, Malik Boudiaf +5

Proprietary and closed APIs are becoming increasingly common to process natural language, and are impacting the practical applications of natural language processing, including few…

cs.LG2023

Data-driven Reachability using Christoffel Functions and Conformal Prediction

Abdelmouaiz Tebjou, Goran Frehse, Faïcel Chamroukhi

An important mathematical tool in the analysis of dynamical systems is the approximation of the reach set, i.e., the set of states reachable after a given time from a given initial…

stat.ML20233 cited

Interpretable learning of effective dynamics for multiscale systems

Emmanuel Menier, Sebastian Kaltenbach, Mouadh Yagoubi +2

The modeling and simulation of high-dimensional multiscale systems is a critical challenge across all areas of science and engineering. It is broadly believed that even with today'…

cs.CY20232 cited

On the Computation of Accessibility Provided by Shared Mobility

Severin Diepolder, Andrea Araldo, Tarek Chouaki +3

Shared Mobility Services (SMS), e.g., Demand-Responsive Transit (DRT) or ride-sharing, can improve mobility in low-density areas, often poorly served by conventional Public Transpo…

cs.LG2023

Transferable Deep Metric Learning for Clustering

Simo Alami. C, Rim Kaddah, Jesse Read

Clustering in high dimension spaces is a difficult task; the usual distance metrics may no longer be appropriate under the curse of dimensionality. Indeed, the choice of the metric…