Français
High dimensional mean estimation - Lecture 2
Multi angle
Authors : Lugosi, Gábor (Author of the conference)
CIRM (Publisher )
CIRM (Publisher )
Loading the player...
|
Abstract :
Networks are often naturally modeled by random processes in which nodes and edges of the network are added one-by-one, according to some simple stochastic dynamics. Uniform and preferential attachment processes are prime examples of such dynamically growing networks. The statistical problems we address in this talk regard discovering the past of the network when a present-day snapshot is observed. Such problems are sometimes termed 'network archeology'. We present a few results that show that, even in gigantic networks, a lot of information is preserved from the very early days. As the field is still in its infancy, many interesting questions remain to be explored.
Keywords : network archeology; random trees; preferential attachment; broadcasting problem
MSC Codes : Keywords : network archeology; random trees; preferential attachment; broadcasting problem
|
Information on the Video
Film maker : Hennenfent, GuillaumeLanguage : English Available date : 14/01/2022 Conference Date : 16/12/2021 Subseries : Research School arXiv category : Statistics ; Probability ; Computer Science Mathematical Area(s) : Probability & Statistics Format : MP4 (.mp4) - HD Video Time : 00:53:47 Targeted Audience : Researchers Download : https://videos.cirm-math.fr/2021-12-15_Lugosi_Part2.mp4 
|
Information on the Event
Event Title : Meeting in Mathematical Statistics - Machine learning and nonparametric statistics / Rencontres de statistique mathématiqueEvent Organizers : Butucea, Cristina ; Minsker, Stanislav ; Pouet, Christophe ; Spokoiny, Vladimir Dates : 13/12/2021 - 17/12/2021 Event Year : 2021 Event URL : https://conferences.cirm-math.fr/2581.html
Citation Data
DOI : 10.24350/CIRM.V.19867803Cite this video as: Lugosi, Gábor (2021). High dimensional mean estimation - Lecture 2. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19867803 URI : http://dx.doi.org/10.24350/CIRM.V.19867803 |
See Also
- [Multi angle] Adversarial examples in deep networks - Lecture 2 / Author of the conference Bartlett, Peter.
- [Multi angle] Network archeology: a few results and questions - Lecture 1 / Author of the conference Lugosi, Gábor.
- [Multi angle] Benign overfitting - Lecture 1 / Author of the conference Bartlett, Peter.
Bibliography
- DEVROYE, Luc, LERASLE, Matthieu, LUGOSI, Gabor, et al. Sub-Gaussian mean estimators. The Annals of Statistics, 2016, vol. 44, no 6, p. 2695-2725. - https://doi.org/10.1214/16-AOS1440
- LUGOSI, Gábor et MENDELSON, Shahar. Sub-Gaussian estimators of the mean of a random vector. The annals of statistics, 2019, vol. 47, no 2, p. 783-794. - https://doi.org/10.1214/17-AOS1639
- LUGOSI, Gabor et MENDELSON, Shahar. Robust multivariate mean estimation: the optimality of trimmed mean. The Annals of Statistics, 2021, vol. 49, no 1, p. 393-410. - https://doi.org/10.1214/20-AOS1961
- LUGOSI, Gabor et MENDELSON, Shahar. Multivariate mean estimation with direction-dependent accuracy. arXiv preprint arXiv:2010.11921, 2020. - https://arxiv.org/abs/2010.11921
- LUGOSI, Gábor et MENDELSON, Shahar. Mean estimation and regression under heavy-tailed distributions: A survey. Foundations of Computational Mathematics, 2019, vol. 19, no 5, p. 1145-1190. - https://doi.org/10.1007/s10208-019-09427-x
Imagette Video
