Lisa_seminaires Septembre 2011

lisa_seminaires@iro.umontreal.ca

1 participants
2 discussions

Reminder: UdeM-McGill-MITACS machine learning seminar Thurs. Sep. 15th @ 13h30, AA1175
by Guillaume Desjardins 15 Sep '11

15 Sep '11

A reminder for today's talk by Ludovic Arnold. See you there ! ---------- Forwarded message ---------- From: Guillaume Desjardins <guillaume.desjardins(a)gmail.com> Date: Tue, Sep 13, 2011 at 10:26 AM Subject: UdeM-McGill-MITACS machine learning seminar Thurs. Sep. 15th @ 13h30, AA1175 To: lisa_seminaires(a)iro.umontreal.ca A UdeM-McGill-MITACS machine learning seminar will be held this Thursday, July 15th. The talk given by Ludovic Arnold, will take place from 13h30-14h30 in the room AA1175 (pavillon Andre-Aisenstadt, click here<http://maps.google.ca/maps?q=2920,+chemin+de+la+tour&hl=en&z=16&iwloc=A>for directions) at the Université de Montréal. Hope to see you there ! Title: Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles Abstract: In the context of gradient descent for likelihood maximization, the choice of a metric is critical. By using a so-called "natural gradient descent" strategy in which a meaningful metric is chosen, one can benefit from agreeable properties such as invariance w.r.t. parametrization and faster convergence. After an introduction to natural gradient descent in the canonical case of likelihood maximization, I will present a unifying framework for Information Geometric Optimization which gives a new understanding of Evolution Strategies such as CMA-ES, NES, CEM and PBIL.

1 0

UdeM-McGill-MITACS machine learning seminar Thurs. Sep. 15th @ 13h30, AA1175
by Guillaume Desjardins 13 Sep '11

13 Sep '11

A UdeM-McGill-MITACS machine learning seminar will be held this Thursday, July 15th. The talk given by Ludovic Arnold, will take place from 13h30-14h30 in the room AA1175 (pavillon Andre-Aisenstadt, click here<http://maps.google.ca/maps?q=2920,+chemin+de+la+tour&hl=en&z=16&iwloc=A>for directions) at the Université de Montréal. Hope to see you there ! Title: Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles Abstract: In the context of gradient descent for likelihood maximization, the choice of a metric is critical. By using a so-called "natural gradient descent" strategy in which a meaningful metric is chosen, one can benefit from agreeable properties such as invariance w.r.t. parametrization and faster convergence. After an introduction to natural gradient descent in the canonical case of likelihood maximization, I will present a unifying framework for Information Geometric Optimization which gives a new understanding of Evolution Strategies such as CMA-ES, NES, CEM and PBIL.

1 0

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

Lisa_seminaires Septembre 2011