Warning message

Submissions for this form are closed.

Crash Course - Distributed Strategic Learning for Engineers

Speakers: 
Hamidou Tembine
Date: 
Thursday, February 23, 2012 (All day) to Friday, February 24, 2012 (All day)
Location: 
Plateau de Moulon, Supélec, 91192 Gif sur Yvette, France

Following the forthcoming book "Distributed strategic learning for wireless engineers", this tutorial course will revisit the fundamental tools  of distributed strategic learning in view of their applications to wireless networks. The course will be subdivided into a theoretical part where the classical methods and results for distributed learning are introduced, and an application part where practical considerations in engineering are visited. Each part will decline successively the basic tools and applications, the advanced methods and results known today, as well as current research activities.

A precise outline is given below:

First DAY: THEORETICAL NOTIONS

MORNING: (Basic notions)

  •   Markov trees
  •   dynamical systems
  •   stochastic approximation
  •   differential inclusion
  •   Research today: fast convergence of iterative learning patterns, hitting time to a set, frequency of visits

AFTERNOON: (STRATEGY LEARNING and PERFORMANCE ESTIMATIONS)

  •  strategy learning
  •  payoff learning
  •  combined learning (CODIPAS)
  •  heterogeneous learning
  •  hybrid learning
  •  Risk-sensitive strategic learning in dynamic robust games
  •  Research today: Best learning algorithms for stability/performance tradeoff, learning global optima in fully distributed way.

Second DAY: APPLICATIONS TO WIRELESS NETWORKS, COMMUNICATIONS AND NETWORK ECONOMICS

MORNING: (Wireless Networks and COMMUNICATIONS)

  •  Distributed learning for parallel routing and frequency selection
  •  Strategic Learning in user-centric network selection
  •  Combined learning under noise in WLAN
  •  Cost of learning and Quality of Experience (QoE) in LTE
  •  Distributed Learning for Network Security
  •  Learning under uncertainty for Network MIMO
  •  Coalitional learning for cognitive radios
  •  Research today: Why should we care on distributed strategic learning? How to extract useful information from outdated and noisy measurements?

AFTERNOON: (ECONOMICS OF NETWORKS)

  •  Mean field learning for the smart grid
  •  Hierarchical learning for the design of networks
  •  Risk-sensitive for the economics of cloud computing
  •  Research today: Learn how to flatten the peaks in large-scale networks