mblondel.org

Mathieu Blondel // Home

My main research interest is machine learning. Lately, I am particularly interested in:. Mathematical optimization for machine learning,. Differentiable structured layers for neural networks,. Optimal transport and time series. I am a staff research scientist at NTT. Mathieu AT thisdomain DOT org. Our paper "Smooth and Sparse Optimal Transport" was accepted for publication at AISTATS 2018. Our paper "Soft-DTW: a Differentiable Loss Function for Time-Series" was accepted for publication at ICML 2017.

http://www.mblondel.org/

OVERVIEW OF mblondel.org

TRAFFIC RANK

>1,000,000

REVIEWS

0

PAGES IN THIS WEBSITE

4

LINKS TO THIS WEBSITE

CONTACTS

ADDRESSES

SOCIAL LINKS

ONLINE SINCE

WEBSITE DETAILS

SEO

PAGES

SIMILAR SITES

TRAFFIC RANK FOR MBLONDEL.ORG

TODAY'S RATING

>1,000,000

TRAFFIC RANK - AVERAGE PER MONTH

BEST MONTH

September

AVERAGE PER DAY Of THE WEEK

HIGHEST TRAFFIC ON

Thursday

TRAFFIC BY CITY

Sign up

CUSTOMER REVIEWS

Average Rating: 3.8 out of 5 with 13 reviews

5 star

5

4 star

3

3 star

4

2 star

0

1 star

1

Hey there! Start your review of mblondel.org

AVERAGE USER RATING

Write a Review

WEBSITE PREVIEW

LOAD TIME

0.6 seconds

FAVICON PREVIEW

16x16
32x32
64x64
128x128
160x160
192x192

CONTACTS AT MBLONDEL.ORG

Blondel Mathieu

Blondel Mathieu

52, rue ●●●●●●●●squieres

L●s , 59120

FR

33.3●●●●6956

ma●●@ffworld.com

View this contact

Blondel Mathieu

52, rue ●●●●●●●●squieres

L●s , 59120

FR

33.3●●●●6956

ma●●@ffworld.com

View this contact

Blondel Mathieu

52, rue ●●●●●●●●squieres

L●s , 59120

FR

33.3●●●●6956

ma●●@ffworld.com

View this contact

ADD CONTACT

Login

TO VIEW CONTACTS

Remove Contacts

FOR PRIVACY ISSUES

DOMAIN REGISTRATION INFORMATION

REGISTERED: n/a
UPDATED: 2014 January 07
EXPIRATION: EXPIRED REGISTER THIS DOMAIN

BUY YOUR DOMAIN

NAME SERVERS

1: sdns2.ovh.net
2: ns310467.ovh.net

REGISTRAR

Gandi SAS (R42-LROR)

WHOIS : whois.publicinterestregistry.net

REFERRED :

CONTENT

PAGES IN
THIS WEBSITE

4

SSL

EXTERNAL LINKS

27

SITE IP

192.30.252.153

LOAD TIME

0.633 sec

SCORE

6.2

PAGE TITLE

Mathieu Blondel // Home | mblondel.org Reviews

<META> DESCRIPTION

My main research interest is machine learning. Lately, I am particularly interested in:. Mathematical optimization for machine learning,. Differentiable structured layers for neural networks,. Optimal transport and time series. I am a staff research scientist at NTT. Mathieu AT thisdomain DOT org. Our paper Smooth and Sparse Optimal Transport was accepted for publication at AISTATS 2018. Our paper Soft-DTW: a Differentiable Loss Function for Time-Series was accepted for publication at ICML 2017.

<META> KEYWORDS

1 mathieu blondel

2 publications

3 talks

4 software

5 data

6 research interest

7 affiliation

8 communication science laboratories

9 kyoto japan

10 news

CONTENT

Page content here

KEYWORDS ON PAGE

mathieu blondel,publications,talks,software,data,research interest,affiliation,communication science laboratories,kyoto japan,news,on the web,twitter,4k followers,github,1k followers,gist,google scholar

SERVER

GitHub.com

CONTENT-TYPE

utf-8

GOOGLE PREVIEW

Mathieu Blondel // Home | mblondel.org Reviews

https://mblondel.org

My main research interest is machine learning. Lately, I am particularly interested in:. Mathematical optimization for machine learning,. Differentiable structured layers for neural networks,. Optimal transport and time series. I am a staff research scientist at NTT. Mathieu AT thisdomain DOT org. Our paper "Smooth and Sparse Optimal Transport" was accepted for publication at AISTATS 2018. Our paper "Soft-DTW: a Differentiable Loss Function for Time-Series" was accepted for publication at ICML 2017.

INTERNAL PAGES

mblondel.org

1

Mathieu Blondel // Talks

http://mblondel.org/talks

Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms. [ slides. Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms. Nagoya Institute of Technology, August 2016. Hosted by Ichiro Takeuchi. Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms. Kyoto University, July 2016. Hosted by Marco Cuturi. Convex Factorization Machines. [ slides. University of Cambridge, September 2015.

2

Mathieu Blondel // Data

http://mblondel.org/data

Amazon7 is a dataset that we created from raw data. Amazon7 pkl.tar.bz2. For Python users, the easiest way to load the dataset is to use joblib. S pickle functionalities. Note that joblib is also part of scikit-learn. As sklearn.externals.joblib. After decompressing the above archive, you can load the dataset as follows:. Alternatively, you may want to use:. Amazon7 uncompressed pkl.tar.bz2. 204 MB download, 1.5 GB uncompressed). The advantage is that the data can be loaded with mmap:.

3

Mathieu Blondel // Software

http://mblondel.org/code

Is a Python/Cython library for large-scale linear classification and regression. It also contains the source code of my paper "Block Coordinate Descent Algorithms for Large-scale Sparse Multiclass Classiﬁcation". Is an easy-to-use and efficient machine learning library for the Python scientific ecosystem. I am a core developer. Is a handwriting recognition project for Chinese and Japanese characters. Tegaki is multi-plaform and supports several recognition engines. I am the main developer.

4

Mathieu Blondel // Publications

http://mblondel.org/publications

Optimization for machine learning. Akinori Fujino, Naonori Ueda, Masakazu Ishihata. In Proceedings of Neural Information Processing Systems ( NIPS. Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms. Masakazu Ishihata, Akinori Fujino, Naonori Ueda. In Proceedings of International Conference on Machine Learning ( ICML. Akinori Fujino, Naonori Ueda. Large-scale Multiclass Support Vector Machine Training via Euclidean Projection onto the Simplex. Journal of Machin...

UPGRADE TO PREMIUM TO VIEW 0 MORE

TOTAL PAGES IN THIS WEBSITE

4

LINKS TO THIS WEBSITE

fa.bianp.net

I say things - SciPy

http://fa.bianp.net/tag/scipy.html

Numerical optimizers for Logistic Regression. Mon 20 May 2013. In this post I compar several implementations of Logistic Regression. The task was to implement a Logistic Regression model using standard optimization tools from. And compare them against state of the art implementations such as LIBLINEAR. In this blog post I'll write down all the implementation details of this model, in the hope that not only the conclusions but also the process would be useful for future comparisons and benchmarks. Begin{a...

fa.bianp.net

Publications

http://fa.bianp.net/pages/publications.html

Here are my most recent publications. A similar list can also be found in my Google Scholar profile. On the convergence rate of the three operator splitting scheme. Word meaning in the ventral visual path: a perceptial to conceptual gradient of semantic coding.". Borghesani, Valentina, Fabian Pedregosa, Marco Buiatti, Alexis Amadon, Evelyn Eger, and Manuela Piazza. NeuroImage (2016) HTTP. Asaga: Asynchronous Parallel Saga. Rémi Leblond, Fabian Pedregosa, Simon Lacoste-Julien, preprint, ArXiv. Borghesani,...

fa.bianp.net

I say things - Job

http://fa.bianp.net/tag/job.html

Job Offer: data scientist in Paris. Fri 10 July 2015. And I are looking looking for a data scientist to work on large-scale non-smooth optimization methods and other topics. You can find more information in this link. The job description is intentionally vague, and depending on the candidate this can be a postdoc-like job with most of their time devoted to research or an engineering-like job with more emphasis on coding tasks and contributing to open source projects. Page 1 / 1.

fa.bianp.net

I say things - ranking

http://fa.bianp.net/tag/ranking.html

Thu 02 May 2013. TL;DR: I've implemented a logistic ordinal regression or proportional odds model. Here is the Python code. Model, also known as the proportional odds was introduced in the early 80s by McCullagh [. And is a generalized linear model specially tailored for the case of predicting ordinal variables, that is, variables that are discrete (as in classification) but which can be ordered (as in regression). It can be seen as an extension of the logistic regression model to the ordinal setting.

fa.bianp.net

I say things - machine learning

http://fa.bianp.net/tag/machine-learning.html

A fast, fully asynchronous variant of the SAGA algorithm. Wed 12 October 2016. My friend Rémi Leblond. Has recently uploaded to ArXiv our preprint on an asynchronous version of the SAGA optimization algorithm. The main contribution is to develop a parallel (fully asynchronous, no locks) variant of the SAGA algorighm. The core of the asynchronous algorithm is similar to Hogwild! The speedups obtained versus the sequential version are quite impressive. For example, we have observed to commonly obtain 5...

fa.bianp.net

I say things - Python

http://fa.bianp.net/tag/python.html

Fri 25 March 2016. Announce: first public release of lightning. A library for large-scale linear classification, regression and ranking in Python. The library was started a couple of years ago by Mathieu Blondel. Who also contributed the vast majority of source code. I joined recently its development and decided it was about time for a v0.1! Prebuild conda packages are available for all operating systems (god thank appveyor). More information on lightning's website. Sun 06 March 2016. Mon 22 February 2016.

fa.bianp.net

I say things - Jupyter

http://fa.bianp.net/tag/jupyter.html

Tue 21 April 2015. TL;DR I created a gallery for IPython/Jupyter notebooks. Check it out :-). A couple of months ago I put online a website that displays a collection of IPython/Jupyter notebooks. The is a website that collects user-submitted and publicly available notebooks and displays them with a nice screenshot. The great thing about this website compared to other. I would like to make a website where it is possible to. Under the hood there's a django app, for which the source code lives here. Don't ...

fa.bianp.net

I say things - fMRI

http://fa.bianp.net/tag/fmri.html

Data-driven hemodynamic response function estimation. Fri 05 December 2014. My latest research paper. Deals with the estimation of the hemodynamic response function (HRF) from fMRI data. This is an important topic since the knowledge of a hemodynamic response function is what makes it possible to extract the brain activation maps that are used in most of the impressive applications of machine learning to fMRI, such as (but not limited to) the reconstruction of visual images from brain activity [.

fa.bianp.net

I say things - consistency

http://fa.bianp.net/tag/consistency.html

On the consistency of ordinal regression methods. Fri 09 October 2015. My latests work (with Francis Bach. Is on the consistency of ordinal regression methods. It has the wildly imaginative title of "On the Consistency of Ordinal Regression Methods" and is currently under review but you can read the draft of it on ArXiv. If you have any thoughts about it, please leave me a comment! Having Fisher consistency is an important property that "allows us to design good loss functions with desirable properties"[.

fa.bianp.net

I say things - memory

http://fa.bianp.net/tag/memory.html

Different ways to get memory consumption or lessons learned from ` memory profiler`. Thu 25 July 2013. As part of the development of memory profiler. I've tried several ways to get memory usage of a program from within Python. In this post I'll describe the different alternatives I've tested. Is a python library that provides an interface for retrieving information on running processes. It provides convenient, fast and cross-platform functions to access the memory usage of a Python module:. From version ...

UPGRADE TO PREMIUM TO VIEW 17 MORE

TOTAL LINKS TO THIS WEBSITE

27

SOCIAL ENGAGEMENT

mblondel_ja

OTHER SITES

mblondass.skyrock.com

Mblondass's blog - ಌ Ҽsƿɑñσℓ & Frɑɑnςάise ; Hɑάn Tu Kïîff HҼiYN - Skyrock.com

More options ▼. Subscribe to my blog. Created: 06/07/2009 at 9:27 AM. Updated: 26/04/2012 at 11:56 AM. 3212; Ҽsƿɑñσℓ and Frɑɑnςάise ; Hɑάn Tu Kïîff HҼiYN. Ami(Ҽ)s - - AccҼƿtés! Fɑns - - AccҼƿtés! Commentɑires - AccҼƿté. Plagiɑt d'idéҼs - Refusé. MҼ PɑrlҼr - - ƿossiblҼ. 1828;)Soit jeune, stylée, droguer, dévergondé et tait toi. All of Mblondass's articles are secret. See their secret blog. Subscribe to my blog! Post to my blog. Here you are free.

mblonde.skyrock.com

Blog de MBlonDe - SchTroMpFette_BlonDe - Skyrock.com

Mot de passe :. J'ai oublié mon mot de passe. BlonDe qi DliR tt Le tps! A tjs La pEchE mai è 2 tenS! Welcome Ds mon MonDe! Mise à jour :. Abonne-toi à mon blog! N'oublie pas que les propos injurieux, racistes, etc. sont interdits par les conditions générales d'utilisation de Skyrock et que tu peux être identifié par ton adresse internet (67.219.144.114) si quelqu'un porte plainte. Ou poster avec :. Retape dans le champ ci-dessous la suite de chiffres et de lettres qui apparaissent dans le cadre ci-contre.

mblonde53.wordpress.com

Galerie Photos Michel et Domi | L'oeil dans le viseur pour capturer l'instant

Galerie Photos Michel et Domi. Beijing – Moscou. 02-Beijing : Le Temple du Ciel. 03-Beijing : Le Palais d’été. 05-Beijing : Maison de thé. 06-Destination Oulan-Bator, capitale de la Mongolie. 07-Le parc national de Gorkhi-Terelj. 08-Le centre de méditation d’Aryaval. 09-Un hôtel en plein air : Un camp de Yourtes. 10-La statue équestre de Gengis Khan. 13-« La Russie Impériale ». 14-De Oulan-Bator à Oulan-Oude. 15-Aux environs d’Oulan-Oude. 18-Accueil dans une famille Bouriate. 30-Kazan : Faubourg Tatar.

mblonde54410.skyrock.com

Blog de Mblonde54410 - moi & la musique <3 - Skyrock.com

Mot de passe :. J'ai oublié mon mot de passe. Plus d'actions ▼. S'abonner à mon blog. Création : 20/04/2012 à 18:51. Mise à jour : 20/04/2012 à 18:51. Moi and la musique 3. Je suis du 54. P facebook morgane.demande moi :). N'oublie pas que les propos injurieux, racistes, etc. sont interdits par les conditions générales d'utilisation de Skyrock et que tu peux être identifié par ton adresse internet (67.219.144.114) si quelqu'un porte plainte. Ou poster avec :. Posté le vendredi 20 avril 2012 18:55.

mblondel.ch

Michel Blondel | Vente directe fruits et légumes Crissier

PRODUITS DE LA FERME. Marché à la Place de la Riponne. Vins de notre vignoble. Produits issus de la ferme. Miel, Confitures, Raisinée, Huile de Noix, …. Grand Marché à la Ferme. Au printemps et en automne. Un Jardin d’Eden. Dans l’Ouest Lausannois. Vente directe fruits et légumes Crissier. La famille Blondel travaille depuis trois générations, les terres du Domaine de la Blancherie à Crissier. Michel et Eliane Blondel. Production intégrée - Arboriculture - Viticulture. Rue d'Yverdon 19 - CH 1023 Crissier.

mblondel.org

Mathieu Blondel // Home

My main research interest is machine learning. Lately, I am particularly interested in:. Mathematical optimization for machine learning,. Differentiable structured layers for neural networks,. Optimal transport and time series. I am a staff research scientist at NTT. Mathieu AT thisdomain DOT org. Our paper "Smooth and Sparse Optimal Transport" was accepted for publication at AISTATS 2018. Our paper "Soft-DTW: a Differentiable Loss Function for Time-Series" was accepted for publication at ICML 2017.

mblondi.wordpress.com

F&m | Muzika i film

The Hobbit: An Unexpected Journey (2012). Upravo je objavljen prvi trejler za film Hobit: Neočekivano putovanja Pitera Džeksona. Film predstavlja dešavanja koja su predhodila kultnom serijalu Gospodar prstenova, a radnja se bavi hobitom Bilbo Baginsom koji putuje u izgubljeno kraljevstvo Erebor gde vlada zmaj Šmaug. Bilbo će se susresti sa Golumom i videti prsten po prvi put. MY PRECIOUS! Film će biti snimljen u 3D tehnici i dolazi u bioskope u decembru 2012. godine. Posted in Filmovi :). Rajan Rejnolds ...

mblondie614.deviantart.com

mblondie614 (misty) - DeviantArt

Window.devicePixelRatio*screen.width 'x' window.devicePixelRatio*screen.height) :(screen.width 'x' screen.height) " class="mi". Window.devicePixelRatio*screen.width 'x' window.devicePixelRatio*screen.height) :(screen.width 'x' screen.height) ". Join DeviantArt for FREE. Forgot Password or Username? Deviant for 10 Years. This deviant's full pageview. Last Visit: 217 weeks ago. This is the place where you can personalize your profile! By moving, adding and personalizing widgets. Why," you ask? Finally upda...

mblondiiie.skyrock.com

Blog de Mblondiiie - Brownie - Skyrock.com

Mot de passe :. J'ai oublié mon mot de passe. Je m'appelle Marine et je ne suis pas dans la norme. Mise à jour :. Joie de vivre ♥. Https:/ www.youtube.com/watch? Abonne-toi à mon blog! Je ne me connecterai que rarement maintenant, sorry guys. Lundi 03 août 2015 04:06. N'oublie pas que les propos injurieux, racistes, etc. sont interdits par les conditions générales d'utilisation de Skyrock et que tu peux être identifié par ton adresse internet (67.219.144.114) si quelqu'un porte plainte. Ou poster avec :.

mblondine.skyrock.com

Blog de Mblondine - Mblondine - Skyrock.com

Mot de passe :. J'ai oublié mon mot de passe. Plus d'actions ▼. S'abonner à mon blog. Création : 01/01/2015 à 15:50. Mise à jour : 31/03/2015 à 07:49. Ajouter cette vidéo à mon blog. Tu veux des kiffs, des commentaires ou autre? 1kiff sur chaque article - 15clicks 1like de la vidéo. 10 commentaires - 3clicks. 20 commentaires - 6clicks. 50 commentaires - 20clicks 1like de la vidéo. 100 commentaires un lien - Partage cette vidéo sur facebook ou ton skyblog. Tu as d'autre proposition? Ou poster avec :.

mblondinette.skyrock.com

Blog de mblondinette - La blonde & les piiires - Skyrock.com

Mot de passe :. J'ai oublié mon mot de passe. La blonde and les piiires. Voilà moi, marine, la blonde et ses piiires! Mise à jour :. Abonne-toi à mon blog! Et oui toutes sur l'escalator et c'est la descente! Trop nul le commentaire mais faut bien mettre quelque chose. N'oublie pas que les propos injurieux, racistes, etc. sont interdits par les conditions générales d'utilisation de Skyrock et que tu peux être identifié par ton adresse internet (67.219.144.114) si quelqu'un porte plainte. Ou poster avec :.