SEMINARS

MonthWeekDay
January 2020
Monday Tuesday Wednesday Thursday Friday Saturday Sunday
December 30, 2019 December 31, 2019 January 1, 2020 January 2, 2020 January 3, 2020 January 4, 2020 January 5, 2020
January 6, 2020 January 7, 2020 January 8, 2020 January 9, 2020

Category: SeminarsKeynote: Radu Horaud

Keynote: Radu Horaud
January 10, 2020 January 11, 2020 January 12, 2020
January 13, 2020 January 14, 2020 January 15, 2020 January 16, 2020

Category: SeminarsCapacity of a LoRaWAN cell, by Martin Heusse (Drakkar)

Capacity of a LoRaWAN cell, by Martin Heusse (Drakkar)
January 17, 2020 January 18, 2020 January 19, 2020
January 20, 2020 January 21, 2020 January 22, 2020 January 23, 2020

Category: SeminarsCan random matrices change the future of machine learning? by Romain Couillet (Gipsa)

Can random matrices change the future of machine learning? by Romain Couillet (Gipsa)
January 24, 2020 January 25, 2020 January 26, 2020
January 27, 2020 January 28, 2020 January 29, 2020 January 30, 2020

Category: GeneralHDR Nicolas Gast

HDR Nicolas Gast
January 31, 2020 February 1, 2020 February 2, 2020
  • December 20, 2019 @ Bâtiment IMAG (amphitheater) -- HDR defense of Panayotis Mertikopoulos (Polaris)

    Online optimization and learning in games: Theory and applications

    HDR Jury:
    - M. Jérôme Bolte (TSE / Univ. Toulouse 1 Capitole, rapporteur)
    - M. Nicolò Cesa-Bianchi (Univ. Milan, rapporteur)
    - M. Sylvain Sorin (Sorbonne Université, rapporteur)
    - M. Eric Gaussier (Univ. Grenoble Alpes, examinateur)
    - M. Josef Hofbauer (Univ. Vienne, examinateur)
    - M. Anatoli Juditsky (Univ. Grenoble Alpes, examinateur)
    - M. Jérôme Renault (TSE / Univ. Toulouse 1 Capitole, examinateur)
    - M. Nicolas Vieille (HEC Paris, examinateur)

    The traditional "pot de soutenance" will take place right after the defense at the ground floor of the IMAG building.

  • January 9, 2020 @ -- Keynote: Radu Horaud
  • January 16, 2020 @ Bâtiment IMAG (406) -- Capacity of a LoRaWAN cell, by Martin Heusse (Drakkar)

    We propose a model to estimate the packet delivery rate in a LoRaWAN cell, when all nodes have the same traffic generation process and may use repetitions. The model predicts the transmission success rate for any cell range and node density, with similar traffic from all nodes. We find that the transmission success depends on striking a balance between the adverse effects of attenuation and collisions; in small cells, it is highly dependent on the suitable allocation of spreading factors, whereas using packet repetitions is more effective in large cells.

  • January 23, 2020 @ -- Can random matrices change the future of machine learning? by Romain Couillet (Gipsa)

    Romain COUILLET (professor at CentraleSupélec, University ParisSaclay; IDEX GSTATS Chair & MIAI LargeDATA Chair, University Grenoble-Alpes)
    Title: Can random matrices change the future of machine learning?
    Abstract: Many standard machine learning algorithms and intuitions are known to misbehave, if not dramatically collapse, when operated on large dimensional data. In this talk, we will show that large dimensional statistics, and particularly random matrix theory, not only can elucidate this behavior but provides a new set of tools to understand and (sometimes drastically) improve machine learning algorithms. Besides, we will show that our various theoretical findings are provably applicable to very realistic and not-so-large dimensional data.

  • January 30, 2020 @ Bâtiment IMAG (amphitheater) -- HDR Nicolas Gast

    TBA

  • February 6, 2020 @ -- keynote LIG

Comments are closed.