SEMINARS

MonthWeekDay
December 2018
Monday Tuesday Wednesday Thursday Friday Saturday Sunday
November 26, 2018 November 27, 2018 November 28, 2018 November 29, 2018

Category: SeminarsDeep learning architectures and training methods by Loris Felardos (Inria + IBPC)

Deep learning architectures and training methods by Loris Felardos (Inria + IBPC)
November 30, 2018 December 1, 2018 December 2, 2018
December 3, 2018 December 4, 2018 December 5, 2018 December 6, 2018

Category: Seminarskeynote du LIG

keynote du LIG
December 7, 2018 December 8, 2018 December 9, 2018
December 10, 2018 December 11, 2018 December 12, 2018 December 13, 2018

Category: SeminarsLearning with minimal information in continuous games, by Mario Bravo (Univ. de Chile)

Learning with minimal information in continuous games, by Mario Bravo (Univ. de Chile)
December 14, 2018 December 15, 2018 December 16, 2018
December 17, 2018 December 18, 2018

Category: SeminarsReservation Strategies for Stochastic Jobs by Guillaume Aupy (Inria Bordeaux)

Reservation Strategies for Stochastic Jobs by Guillaume Aupy (Inria Bordeaux)
December 19, 2018 December 20, 2018 December 21, 2018 December 22, 2018 December 23, 2018
December 24, 2018 December 25, 2018 December 26, 2018 December 27, 2018 December 28, 2018 December 29, 2018 December 30, 2018
December 31, 2018 January 1, 2019 January 2, 2019 January 3, 2019 January 4, 2019 January 5, 2019 January 6, 2019
  • November 22, 2018 @ Bat IMAG, 306 -- Conception et analyse des systèmes IoT : les promesses de l’approche systèmes complexes, by Pascale Primet (Inria, Lyon)

    L’Internet des Objets (IoT) est l'extension d’Internet à des dispositifs et à des lieux du monde physique. Cette extension ouvre de nombreuses opportunités techniques et économiques mais, comme toute technologie nouvelle, apporte de multiples questions scientifiques, environnementales, éthiques and sociétales. Ainsi, malgré l’explosion du nombre de déploiements “internet des objets” à des fins de preuves de concepts, la mise en oeuvre opérationnelle de l’IoT est freinée par la lenteur des décisions, la complexité et les risques de la technologie et de ses applications.
    Nous pensons que la théorie des systèmes complexes est un outil particulièrement pertinent pour étudier ces questions difficiles et aider à la conception et à l’analyse des systèmes et des services d’objets connectés.
    Dans cet explosé, nous illustrons, au travers d’exemples concrets, les caractéristiques spécifiques “système complexe” des environnements IoT. Nous présentons ensuite le modèle conceptuel basé sur des agents, que nous développons dans la plate-forme StackiLab pour caractériser et modéliser un système IoT dynamique afin d’en construire un “jumeau numérique” personnalisé et évolutif. Nous montrons comment la simulation de scénarios basés sur l'instantiation de ce modèle permettrait la mise en perspective de différentes solutions d’architecture, de dimensionnement, de planification, de choix technologiques ou d’étudier, à partir d’une même représentation abstraite, des questions orthogonales telles que la rentabilité économique, l’analyse des risques, l’analyse des performances.
    Enfin nous ouvrons la discussion sur la complémentarité et la possible integration de cette approche avec les méthodes classiques de modélisation et d’analyse de réseaux et de systèmes distribués pour affiner notre compréhension de ces systèmes.

  • November 29, 2018 @ Bâtiment IMAG (406) -- Deep learning architectures and training methods by Loris Felardos (Inria + IBPC)

    The past few years have seen a dramatic increase in the performance of deep learning architectures applied to fields ranging from computer vision and speech recognition to bio-informatics and drug design. This presentation will consist in three parts. Part 1 is an gentle introduction to the basic ideas that are crucial for training deep neural networks (like logistic regression, SGD and optimization methods). Part 2 focuses on the most common building blocks (convolutions, attention layers and skip connections) of practical neural architectures such as recurrent neural networks, generative models and the more recent graph convolutional networks. Finally, part 3 insists on the importance of carefully designed loss functions across a range a different training methods (may it be for supervised, semi-supervised or unsupervised learning).

  • December 6, 2018 @ -- keynote du LIG
  • December 13, 2018 @ Bâtiment IMAG (406) -- Learning with minimal information in continuous games, by Mario Bravo (Univ. de Chile)

    In this talk we introduce a learning process for games with continuous action sets. The procedure is payoff-based and thus requires no sophistication from players and no knowledge of the game. We show that despite such limited information, players will converge to Nash in large classes of games (possibly with a continuum of equilibria). In particular, convergence to stable Nash equilibrium is guaranteed in all games with strategic complements as well as in concave games. Time permitting, we will also discuss convergence results for locally ordinal potential games and games with isolated equilibria.

    This is joint work with Sebastian Bervoets and Mathieu Faure.

  • December 18, 2018 @ Bâtiment IMAG (406) -- Reservation Strategies for Stochastic Jobs by Guillaume Aupy (Inria Bordeaux)

    We are interested in scheduling stochastic jobs on a reservation-based
    platform. Specifically, we consider jobs whose execution time follows a
    known probability distribution. The platform is reservation-based,
    meaning that the user has to request fixed-length time slots. The cost
    depends on both the request duration and the actual execution time of
    the job. A reservation strategy is a sequence of increasing-length
    reservations, which are paid for until one of them allows the job to
    successfully complete. The goal is to minimize the total expected cost
    of the strategy. I will present different scheduling strategies and
    properties of an optimal solution.

  • January 10, 2019 @ Bâtiment IMAG (406) -- Best-of-two-worlds analysis of online search, by Christopher Durr (Lip6)

    Best-of-two-worlds analysis of online search

    In search problems, a mobile searcher seeks to locate a target that hides in some unknown position of the environment. Such problems are typically considered to be of an on-line nature, in that the input is unknown to the searcher, and the performance of a search strategy is usually analyzed by means of the standard framework of the competitive ratio, which compares the cost incurred by the searcher to an optimal strategy that knows the location of the target. However, one can argue that even for simple search problems, competitive analysis fails to distinguish between strategies which, intuitively, should have different performance in practice.

    Motivated by the above, in this work we introduce and study measures supplementary to competitive analysis in the context of search problems. In particular, we focus on the well-known problem of linear search, informally known as the cow-path problem, for which there is an infinite number of strategies that achieve an optimal competitive ratio equal to 9. We propose a measure that reflects the rate at which the line is being explored by the searcher, and which can be seen as an extension of the bijective ratio over an uncountable set of requests. Using this measure we show that a natural strategy that explores the line aggressively is optimal among all 9-competitive strategies. This provides, in particular, a strict separation from the competitively optimal doubling strategy, which is much more conservative in terms of exploration. We also provide evidence that this aggressiveness is requisite for optimality, by showing that any optimal strategy must mimic the aggressive strategy in its first few explorations.

    joint work with Spyros Angelopoulos and Shendan Jin

Comments are closed.