[seminarios-mlpb] Reminder: seminar talk tomorrow
- From: Miguel Almeida <miguel.almeida@xxxxxxxxxxx>
- To: "seminarios-mlpb@xxxxxxxxxxxxx" <seminarios-mlpb@xxxxxxxxxxxxx>
- Date: Mon, 10 Nov 2014 11:30:23 +0000
Hello all,
We will have a seminar tomorrow, presented by Prof. João Xavier, of ISR. See
you there!
Miguel
********************************************************************
TALK ANNOUNCEMENT -- Anfiteatro do Complexo Interdisciplinar
********************************************************************
Priberam Machine Learning Lunch Seminar
Speaker: João Xavier (ISR)
Venue: IST Alameda, Anfiteatro do Complexo Interdisciplinar
Date: Tuesday, November 11th, 2014
Time: 13:00
Lunch will be provided
Title:
Distributed detection over random networks
Abstract:
A team of agents collaborate to distinguish between two states of nature.
Agents receive private measurements and exchange messages with neighbors to
collectively solve the detection problem. We consider the challenging scenario
of communication networks with time-variant random topologies thereby embracing
several models of link erasure, packet drops and gossip-like randomized
protocols.
We suggest a consensus+innovations distributed detector and characterize its
performance. We show that an interesting phase-transition phenomenon emerges:
if the random connectivity model is fast enough for the given hypothesis test,
each agent is asymptotically equivalent to a (virtual) central node that sees
all network measurements instantaneously. Moreover, the threshold for the
equivalence depends on the hypothesis' distributions at stake, and not only on
their Chernoff distance as in classical centralized detection.
Our proofs draw from large-deviations theory and convex analysis, and introduce
novel results in random matrix theory.
Bio:
João Xavier is with the Electrical and Computer Engineering (ECE) Department at
Instituto Superior Técnico (IST) and the Instituto de Sistemas e Robótica (ISR).
His current research focus on distributed estimation, detection and
optimization for large-scale networks.
********************************************************************
General info about our seminars:
http://labs.priberam.com/Academia-Partnerships/Seminars.aspx
Please forward this link to whoever might be interested in attending the
seminars.
Other related posts:
