[Lisa_seminaires] [Tea Talk] Brady Neal (MILA) Fri Apr 4 10:30AM AA1360

Michael Noukhovitch mnoukhov at gmail.com
Ven 6 Avr 10:24:33 EDT 2018


And announcing for the first time ever this talk will be **LIVESTREAMED**

Watch the livestream here (but please mute your microphone)
https://bluejeans.com/809027115/browser

On Fri, Apr 6, 2018 at 10:07 AM Michael Noukhovitch <mnoukhov at gmail.com>
wrote:

> Reminder this is in 20 minutes!
>
> On Wed, Apr 4, 2018, 12:35 Michael Noukhovitch <mnoukhov at gmail.com> wrote:
>
>> This week we have our very own *Brady Neal* giving a talk this *Friday*
>> at *10:30AM* in room *AA1360*.
>>
>> I may be a little bit biased, but coming to this talk will be at least
>> one standard deviation better than your usual Friday!
>> Michael
>>
>> *TITLE *Towards Understanding Generalization in Deep Learning by
>> Revisiting the Bias-Variance Decomposition
>>
>> *KEYWORDS *DL Theory, ML Theory
>>
>>
>> *ABSTRACT*Generalization is at the very core of machine learning. The
>> bias-variance decomposition in machine learning is an underused lens to
>> view generalization through. While it’s more common to derive upper bounds
>> on the generalization gap via more complicated measures of complexity such
>> as the VC dimension and Rademacher complexity, the bias-variance
>> decomposition is an *equality* that is noticeably simpler. Looking
>> through this lens, we can quickly get to partial explanations for why
>> larger neural networks seem to generalize better than their smaller
>> counterparts, despite the fact that bounds based on VC dimension and
>> Rademacher complexity suggest the opposite. We appeal to some of the
>> blessings of high dimensionality to do this.
>>
>> While Zhang et al. (2017) were quite surprised by the results of their
>> experiments in “Understanding deep learning requires rethinking
>> generalization,” they would have been much less surprised if they were
>> looking at their results through the lens of the bias-variance
>> decomposition.
>>
>>
>> *BIO*Brady was an intern at MILA and is now a Masters student at MILA
>> with Ioannis Mitliagkas. He organizes the DL Theory Reading Group and is
>> currently focused on generalization and optimization in deep learning
>>
>
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20180406/3edbff72/attachment.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires