Activities

Graph classification has recently received a lot of attention from various fields of machine learning e.g. kernel methods, sequential modeling or graph embedding. We address [...]

In this talk, we address a very common and practical question for the programmer: what should be the general architecture of our code? In particular, [...]

Learning from data strutured as a graph usually requires to embed this graph in some vector space of low dimension. The most popular technique relies [...]

Edge computing provides a new way to implement services with many unique advantages. While many edge computing solutions have been implemented within different network infrastructures, [...]

Nathan de Lara will present the article Halko, N., Martinsson, P. G., & Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing [...]

Stochastic network calculus is a tool for computing error bounds on the performance of queueing systems. However, deriving accurate bounds for networks consisting of several [...]

For decades power systems academics have proclaimed the need for real time prices to create a more efficient grid. The rationale is economics 101: proper [...]

The talk is based on the Online Course Convex Optimization by Stephen Boyd and the Book Convex Optimization by Stephen Boyd and Lieven Vandenberghe. Slides [...]

This lecture explores the general problem of explaining the behavior of Artificial Neural Networks (ANN). The goal is to construct a representation which enhances human [...]

In this talk we will discuss optimal control subject to changing conditions (a changing environment). This is an area that recently received a lot of [...]

This tutorial will explain how to easily turn slow Python into fast Python with the numba package. Speed up of X2000 will be demonstrated on [...]

Motivated by the increasing ubiquity of large-scale data collection infrastructures, we investigate how to protect sensitive information in dynamic resource allocation problems. The central question [...]

Abstract: Many learning problems are formulated as minimization of some loss function on a training set of examples. Distributed gradient methods on a cluster are [...]

Modern cities are alive with sensors, such as smartphones, wearables, vehicles, and cameras. Realizing our plans for smart environments of the future necessitates a radical [...]

Workshop LINCS and its Scientific Committee June 19th and 20th, 2018 LINCS  -  23 avenue d’Italie, 4th floor – 75013 Paris Agenda June 19th Welcome [...]

In this talk we will define notions of dimension on unimodular random graphs. The key point in this definition is unimodularity which is used indispensably [...]

Internet interconnections are the means by which networks exchange traffic between one another. These interconnections are typically established in facilities that have known geographic locations, [...]

Machine Learning, as the most successful paradigm of Artificial Intelligence to date, has shown its great potential in restructuring all aspects in our everyday life, [...]

We will talk about the online influence maximization problem in social networks under the independent cascade model. Specifically, we aim to learn the set of [...]

In this talk we introduce a novel information propagation method in Twitter, while maintaining a low computational complexity. The proposed method first employs Joint Complexity, [...]

Social media contain information shared by hundreds of millions of users across the world and provide one of the richest dataset created by human activity. [...]

Hierarchical clustering is a recursive partitioning of a dataset into clusters at an increasingly finer granularity. Motivated by the fact that most work on hierarchical [...]

The problem of predicting connections between a set of data points finds many applications, in systems biology and social network analysis among others. We focus [...]

In this talk, I will present recent works on large-scale similarity search, and show that it is possible to build a graph connecting up to [...]

Clustering is a central problem in machine learning for which graph-based approaches have proven their efficiency. In this paper, we study a relaxation of the [...]

In this talk, I will present a collection of results focusing on the presence of inhomogeneities in networks: from the detection of dense clusters (community [...]

Recent results have characterized the exact information-theoretic threshold for graph matching in correlated Erd?s-Rényi graphs. However, very little is known about the existence of efficient [...]

Money or data transfers, contacts between individuals, or product sales, may all be modeled as temporal interactions. Studying the structure and dynamics of interactions is [...]

This workshop will bring together researchers from both industry and academia for presenting and discussing learning techniques from/with graphs, from both theoretical and practical perspectives. [...]

Fingerprinting networking equipment has many potential applications and benefits in network management and security. More generally, it is useful for the understanding of network structures [...]

Open web proxies promise anonymity and censorship circumvention at no cost. Several websites publish lists of free proxies organized by country, anonymity level, and performance. [...]

Marc-Olivier Buob will present a paper of Scott E. Fahlman and Christian Lebiere about The Cascade-Correlation Learning Architecture, August 29, 1991 CMU-CS-90-100

Confinement of human settlement in areas limited in size is the foundation of the long-standing Central Place Theory which assumes the existence of regular spatial [...]

 Abstract: In this talk, I present our ongoing work on utilising edge-computing to improve the scalability and privacy of user-centred analytics in the context of [...]

In this session of the reading group, Anastasios Giovanidis will present the paper O. Fercoq, M. Akian, M. Bouhtou, S. Gaubert. “Ergodic control and polyhedral [...]

Nathan De Lara will introduce the knowledge graph embeddings, based on the following references: Bordes, A., Usunier, N., Garcia-Duran, A., Weston, J., and Yakhnenko, O. [...]

We propose a novel algorithm for the hierarchical clustering of graphs. The algorithm is a simple but key modification of the Louvain algorithm based on [...]

Orateur : Élie de Panafieu La question qui guidera l'exposé est l'étude de la loi limite du nombre de triangles dans un graphes aléatoire à [...]

In many applications such as cloud computing, managing server farm resources etc. an incoming task or job has to be matched with an appropriate server [...]

Next generation wireless architectures are expected to enable slices of shared wireless infrastructure which are customized to specific mobile operators/services. Given infrastructure costs and the [...]

For the next reading group, Édouard Pineau will talk about sequence-to sequence learning, based on the two following references: Sutskever Ilya, Oriol Vinyals, and Quoc [...]

Abstract: Apple and Samsung have been fighting patent battles around the world. Come learn about the mathematics at the heart of one of these battles, [...]

In this presentation, a completely revisited secure data storage and transmission scheme ispresented. This new scheme is based on an agnostic selective encryption methods combinedwith [...]

Fabien Mathieu will talk about Queuing or not Queuing? (in large systems), and will mainly use the following reference : Load balancing in large-scale systems [...]

Understanding the performance of a pool of servers is crucial for proper dimensioning. One of the main challenges is to take into account the complex [...]

Achille Salaün will talk about Recurrent Neural Networks and present the paper Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling by Chung, Gulcehre, [...]

Although many advantages are expected from the provision of services for M2M communications in cellular networks such as extended coverage, security, robust management and lower [...]

For the next session of the reading group, Céline Comte will talk about Analyzing the M/G/1 queue with a branching process, and will mainly use [...]