Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Duranthon, O"'
Autor:
Duranthon, O., Zdeborová, L.
Publikováno v:
Proceedings of the Third Learning on Graphs Conference (LoG 2024), PMLR 269
While graph convolutional networks show great practical promises, the theoretical understanding of their generalization properties as a function of the number of samples is still in its infancy compared to the more broadly studied case of supervised
Externí odkaz:
http://arxiv.org/abs/2402.03818
Autor:
Duranthon, O., Zdeborová, L.
Publikováno v:
Transactions on Machine Learning Research (TMLR) (03/2024)
The contextual stochastic block model (cSBM) was proposed for unsupervised community detection on attributed graphs where both the graph and the high-dimensional node information correlate with node labels. In the context of machine learning on graph
Externí odkaz:
http://arxiv.org/abs/2306.07948
Autor:
Duranthon, O., Zdeborová, L.
Publikováno v:
Mach. Learn.: Sci. Technol. 4 035017 (2023)
The stochastic block model (SBM) is widely studied as a benchmark for graph clustering aka community detection. In practice, graph data often come with node attributes that bear additional information about the communities. Previous works modeled suc
Externí odkaz:
http://arxiv.org/abs/2303.09995
Autor:
Duranthon, O., Di Molfetta, Giuseppe
Publikováno v:
Phys. Rev. A 103, 032224 (2021)
One can think of some physical evolutions as being the emergent-effective result of a microscopic discrete model. Inspired by classical coarse-graining procedures, we provide a simple procedure to coarse-grain color-blind quantum cellular automata th
Externí odkaz:
http://arxiv.org/abs/2011.04287
We show that the mutual information between the representation of a learning machine and the hidden features that it extracts from data is bounded from below by the relevance, which is the entropy of the model's energy distribution. Models with maxim
Externí odkaz:
http://arxiv.org/abs/1909.12792
Publikováno v:
Natural Computing
Natural Computing, 2022, ⟨10.1007/s11047-022-09879-1⟩
Natural Computing, 2021, 103 (3), pp.032224. ⟨10.1007/s11047-022-09879-1⟩
Natural Computing, 2022, ⟨10.1007/s11047-022-09879-1⟩
Natural Computing, 2021, 103 (3), pp.032224. ⟨10.1007/s11047-022-09879-1⟩
Gauge-invariance is a fundamental concept in Physics -- known to provide mathematical justification for the fundamental forces. In this paper, we provide discrete counterparts to the main gauge theoretical concepts directly in terms of Cellular Autom
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e07869b30f6f4dd9cdaf4e99f649844c
https://hal.science/hal-02557738
https://hal.science/hal-02557738
Autor:
Giuseppe, Di Molfetta, Sellapillay, Kevissen, Arrighi, Pablo, Di Molfetta, Giuseppe, Eon, Nathanaël, Duranthon, O., Manighalam, Michael
Publikováno v:
Quantum Information Processing
Quantum Information Processing, 2021, 20 (2), pp.76. ⟨10.1007/s11128-021-03011-5⟩
Quantum Information Processing, 2021, 20 (2), pp.76. ⟨10.1007/s11128-021-03011-5⟩
A Plastic quantum walk admits both continuous time and continuous spacetime. The model has been recently proposed by one of the authors in Di Molfetta and Arrighi (Quant Inf Process 19(2): 47, 2020), leading to a general quantum simulation scheme for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8318e9d25d564bbdc582da318255294
https://hal-amu.archives-ouvertes.fr/hal-03594720
https://hal-amu.archives-ouvertes.fr/hal-03594720
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Duranthon, O., Marsili, M.
Optimal Learning Machines (OLM) are systems that extract maximally informative representation from data. At a given resolution, they maximise the relevance, which is the entropy of their energy distribution. We show that the relevance lower bounds th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::d3078ad5059f11dace6fc0aafcc292c6
https://hal.archives-ouvertes.fr/hal-02423702
https://hal.archives-ouvertes.fr/hal-02423702