May 2018 - Lisa_seminaires - mailman.iro.umontreal.ca

[Tea Talk] Adrià Recasens (MIT) May 25 2018 1:30 PM AA3195
by Michael Noukhovitch 25 May '18

25 May '18

For our second talk this Friday, we have *Adrià Recasens * from * MIT *on *Friday May 25 2018* at *1:30 PM* in room *AA3195* This talk will be streamed as usual here: https://bluejeans.com/809027115/webrtc and Adrià is open to meetings but we don't know his schedule after his talk yet, if you're interested in meeting with him, shoot me an email For great research discussions, look no further than this talk! Michael *TITLE* Where are they looking? *KEYWORDS *computer vision *ABSTRACT* Humans have the remarkable ability to follow the gaze of other people to identify what they are looking at. Following eye gaze, or gaze-following, is an important ability that allows us to understand what other people are thinking, the actions they are performing, and even predict what they might do next. Despite the importance of this topic, this problem has only been studied in limited scenarios within the computer vision community. In this talk I will present a deep neural network-based approach for gaze-following. Given an image and the location of a head, our approach follows the gaze of the person and identifies the object being looked at. Furthermore, I will also introduce GazeNet, a deep neural-network to predict the 3D direction of a person's gaze from the full 360 degrees. To complement GazeNet, I will present a novel saliency-based sampling layer for neural networks, the Saliency Sampler, which helps to improve the spatial sampling of input data for an arbitrary task. Our differentiable layer can be added as a preprocessing block to existing task networks and trained altogether in an end-to-end fashion. The effect of the layer is to efficiently estimate how to sample from the original data in order to boost task performance. For example, for the gaze-tracking task in which the original data might range in size up to several megapixels, but where the desired input images to the task network are much smaller, our layer learns how best to sample from the underlying high resolution data in a manner which preserves task-relevant information better than uniform downsampling. *BIO* You can read his bio here: https://people.csail.mit.edu/recasens/

1 2

Fwd: [Lisa_teatalk] [Tea Talk] Nicolas Le Roux (Google) May 25 2018 10:30 AM AA3195
by xavier bouthillier 25 May '18

25 May '18

He are the slides from Nicolas' talk. ---------- Forwarded message ---------- From: Nicolas Le Roux <nlr(a)google.com> Date: Fri, May 25, 2018 at 10:32 AM Subject: Re: [Lisa_seminaires] [Lisa_teatalk] [Tea Talk] Nicolas Le Roux (Google) May 25 2018 10:30 AM AA3195 To: xavier.bouthillier(a)gmail.com On Fri, 25 May 2018 at 10:16, xavier bouthillier < xavier.bouthillier(a)gmail.com> wrote: > Salut Nicolas, > > Pour le streaming tu peux te connecter à l'adresse suivante: > https://bluejeans.com/809027115/webrtc > On va faire un share-screen pour partager tes slides en temps réel. Je > vais seulement streamer, je n'enregistrerai pas. > > Le local 3195 est ouvert, tu peux venir t'installer quand tu veux. > > Xavier > > On Tue, May 22, 2018 at 12:45 PM, Nicolas Le Roux <nlr(a)google.com> wrote: > >> For those of you who attended my talk at the Workshop on learning theory, >> this one will fill in some of the gaps I mentioned. >> >> On Tue, 22 May 2018 at 12:17, Michael Noukhovitch <mnoukhov(a)gmail.com> >> wrote: >> >>> This week we will have two tea talks (morning and afternoon) on Friday! >>> Wow! >>> >>> The first talk will be *Nicolas Le* *Roux * on *May 25 2018* at *10:30 >>> AM* in room *AA3195* (note the room change, we'll most likely be in >>> 3195 for the summer). >>> >>> Streaming is, as always, at this link: https://bluejeans.com/ >>> 809027115/webrtc but watch it live because there will be no recordings! >>> >>> Don't waver on going to this talk, it is sure to be invariantly >>> excellent! >>> Michael >>> >>> *TITLE* An exploration of variance reduction techniques in stochastic >>> optimization >>> >>> *KEYWORDS *deep learning theory, optimization >>> >>> *ABSTRACT* >>> I will present recent and ongoing work on reducing the variance in >>> stochastic optimization techniques to speed-up and simplify the resulting >>> algorithms. In particular, stochastic gradient methods can suffer from high >>> variance, limiting their convergence speed. While variance reduction >>> techniques exist in the finite case, they are rarer in the online case. We >>> demonstrate how an increasing momentum offers variance reduction in the >>> online case, at the expense of bias, and how that bias can be countered by >>> an extrapolation step. The resulting algorithm differs from iterate >>> averaging in only a factor, but, in the context of the minimization of a >>> quadratic function, this difference is enough to lead to the first >>> algorithm converging both linearly in the noiseless and sublinearly in the >>> homoscedastic noise case when using a constant stepsize. >>> >>> *BIO* >>> *Nicolas Le Roux got an MSc in Applied Maths from Ecole Centrale Paris >>> and an MSc in Maths, Learning and Vision from ENS Cachan. He got his PhD in >>> 2008 from University of Montreal where he worked with Yoshua Bengio on >>> neural networks in general and their optimisation in particular. He then >>> moved to Microsoft Research Cambridge to work on generative models of >>> images with John Winn. In 2010, he joined Inria in Francis Bach's team to >>> work on large-scale convex optimisation. From 2012 to 2017, he created and >>> managed the research team at Criteo in Paris. He joined Google Brain >>> Montreal in 2017 where he now works on large-scale optimization and >>> reinforcement learning.* >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-montreal-office-hours" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-montreal-office-hours+unsubscribe(a)google.com. >>> To post to this group, send email to brain-montreal-office-hours@ >>> google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-montreal-office-hours/CAMVr0Vy4KsyukWMA_ >>> 7jfFzebONgVbD3Oh7wa%2Bk5eVxta8KYUVg%40mail.gmail.com >>> <https://groups.google.com/a/google.com/d/msgid/brain-montreal-office-hours/…> >>> . >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-mon-fte" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-mon-fte+unsubscribe(a)google.com. >>> To post to this group, send email to brain-mon-fte(a)google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-mon-fte/CAMVr0Vy4KsyukWMA_7jfFzebONgVbD3Oh7wa% >>> 2Bk5eVxta8KYUVg%40mail.gmail.com >>> <https://groups.google.com/a/google.com/d/msgid/brain-mon-fte/CAMVr0Vy4Ksyuk…> >>> . >>> _______________________________________________ >>> Lisa_teatalk mailing list >>> Lisa_teatalk(a)iro.umontreal.ca >>> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_teatalk >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-montreal-office-hours" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-montreal-office-hours+unsubscribe(a)google.com. >>> To post to this group, send email to brain-montreal-office-hours@ >>> google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-montreal-office-hours/CAMVr0Vy4KsyukWMA_ >>> 7jfFzebONgVbD3Oh7wa%2Bk5eVxta8KYUVg%40mail.gmail.com. >>> >>> -- >>> You received this message because you are subscribed to the Google >>> Groups "brain-mon-fte" group. >>> To unsubscribe from this group and stop receiving emails from it, send >>> an email to brain-mon-fte+unsubscribe(a)google.com. >>> To post to this group, send email to brain-mon-fte(a)google.com. >>> To view this discussion on the web visit https://groups.google.com/a/ >>> google.com/d/msgid/brain-mon-fte/CAMVr0Vy4KsyukWMA_7jfFzebONgVbD3Oh7wa% >>> 2Bk5eVxta8KYUVg%40mail.gmail.com. >>> >> >> >> -- >> Nicolas Le Roux >> >> _______________________________________________ >> Lisa_seminaires mailing list >> Lisa_seminaires(a)iro.umontreal.ca >> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_seminaires >> >> > -- Nicolas Le Roux

1 0

[Tea Talk] Nicolas Le Roux (Google) May 25 2018 10:30 AM AA3195
by Michael Noukhovitch 25 May '18

25 May '18

This week we will have two tea talks (morning and afternoon) on Friday! Wow! The first talk will be *Nicolas Le* *Roux * on *May 25 2018* at *10:30 AM* in room *AA3195* (note the room change, we'll most likely be in 3195 for the summer). Streaming is, as always, at this link: https://bluejeans.com/809027115/webrtc but watch it live because there will be no recordings! Don't waver on going to this talk, it is sure to be invariantly excellent! Michael *TITLE* An exploration of variance reduction techniques in stochastic optimization *KEYWORDS *deep learning theory, optimization *ABSTRACT* I will present recent and ongoing work on reducing the variance in stochastic optimization techniques to speed-up and simplify the resulting algorithms. In particular, stochastic gradient methods can suffer from high variance, limiting their convergence speed. While variance reduction techniques exist in the finite case, they are rarer in the online case. We demonstrate how an increasing momentum offers variance reduction in the online case, at the expense of bias, and how that bias can be countered by an extrapolation step. The resulting algorithm differs from iterate averaging in only a factor, but, in the context of the minimization of a quadratic function, this difference is enough to lead to the first algorithm converging both linearly in the noiseless and sublinearly in the homoscedastic noise case when using a constant stepsize. *BIO* *Nicolas Le Roux got an MSc in Applied Maths from Ecole Centrale Paris and an MSc in Maths, Learning and Vision from ENS Cachan. He got his PhD in 2008 from University of Montreal where he worked with Yoshua Bengio on neural networks in general and their optimisation in particular. He then moved to Microsoft Research Cambridge to work on generative models of images with John Winn. In 2010, he joined Inria in Francis Bach's team to work on large-scale convex optimisation. From 2012 to 2017, he created and managed the research team at Criteo in Paris. He joined Google Brain Montreal in 2017 where he now works on large-scale optimization and reinforcement learning.*

2 4

No [Tea Talk] this week
by Michael Noukhovitch 14 May '18

14 May '18

Good luck to everyone rushing for NIPS! Michael

1 0

Re: [Lisa_seminaires] [Tea Talk] Martin Gilbert (IVADO) May 11 2018 10:30 AM AA1360
by Michael Noukhovitch 11 May '18

11 May '18

Reminder: talk is in 30 minutes On Mon, May 7, 2018, 14:14 Michael Noukhovitch <mnoukhov(a)gmail.com> wrote: > This week we have Martin Gilbert from IVADO giving a talk on May 11 2018 > at 10:30 AM in room AA1360 > > See you there! > Michael > > TITLE Intro to Ethics 2 > > KEYWORDS > > ABSTRACT > In this presentation, I will introduce to the three main families of > normative moral theories: consequentialism, deontologism and virtue ethics. > > BIO >

1 0

Re: [Lisa_seminaires] [Lisa_montreal] [Tea Talk] extra talk this afternoon 15:30, AA4488, on Ranking
by Yoshua Bengio 11 May '18

11 May '18

We have an extra tea-talk this afternoon at 15:30 in room AA4488: https://www.gerad.ca/fr/events/1589 A WEIGHTED CORRELATION INDEX FOR RANKINGS WITH TIESSebastiano Vigna <http://vigna.di.unimi.it/> – Università degli Studi di Milano, Italie Understanding the correlation between two different scores for the same set of items is a common problem in information retrieval, and the most commonly used statistics that quantifies this correlation is Kendall's tau. However, the standard definition fails to capture that discordances between items with high rank are more important than those between items with low rank. Recently, a new measure of correlation based on average precision has been proposed to solve this problem, but like many alternative proposals in the literature it assumes that there are no ties in the scores. This is a major deficiency in a number of contexts, and in particular while comparing centrality scores on large graphs, as the obvious baseline, in-degree, has a very large number of ties in web and social graphs. We propose to extend Kendall's definition in a natural way to take into account weights in the presence of ties. We prove a number of interesting mathematical properties of our generalization and describe an O(nlogn) algorithm for its computation. We also validate the usefulness of our weighted measure of correlation using experimental data. > _______________________________________________ > Lisa_montreal mailing list > Lisa_montreal(a)iro.umontreal.ca > https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_montreal > >

1 0

[Tea Talk] Martin Gilbert (IVADO) Fri May 11 2018 10:30 AM AA1360
by Michael Noukhovitch 07 May '18

07 May '18

This week we have our very own, Martin Gilbert from IVADO giving a follow-up on his previous Intro to Ethics talk on *Friday May 11 2018* at *10:30 AM* in room *AA1360* Come to this talk because you'll learn and improve your life, it's your duty as MILA students, and because going to tea talks would be very gracious of you! Michael *TITLE* Intro to Ethics 2 *ABSTRACT* In this presentation, I will introduce to the three main families of normative moral theories: consequentialism, deontologism and virtue ethics.

1 0

[Tea Talk] is cancelled for ICLR
by Michael Noukhovitch 02 May '18

02 May '18

No tea talk this week! Instead find someone to talk to about tea!

1 0