News

Prof. Xavier d’Haultfoeuille won the 2019 AFSE Malinvaud Prize

June, 2019

Prof. Xavier d’Haultfoeuille won the 2019 AFSE Malinvaud Prize. For is paper “Fuzzy Differences-in-Differences” publised in the Review of Economic Studies (2018), co-authored with Clément de Chaisemartin.

Abstract :
Difference-in-differences (DID) is a method to evaluate the effect of a treatment. In its basic version, a “control group” is untreated at two dates, whereas a “treatment group” becomes fully treated at the second date. However, in many applications of the DID method, the treatment rate only increases more in the treatment group. In such fuzzy designs, a popular estimator of the treatment effect is the DID of the outcome divided by the DID of the treatment. We show that this ratio identifies a local average treatment effect only if the effect of the treatment is stable over time, and if the effect of the treatment is the same in the treatment and in the control group. We then propose two alternative estimands that do not rely on any assumption on treatment effects, and that can be used when the treatment rate does not change over time in the control group. We prove that the corresponding estimators are asymptotically normal. Finally, we use our results to reassess the returns to schooling in Indonesia.

https://academic.oup.com/restud/article/85/2/999/4096388

For more information click here.

Prof. Francis Kramarz Elected as Society of Labor Economists Fellow

June, 2019

Professor Francis Kramarz has been named a fellow of the Society of Labor Economists (SOLE). The honorary title is given to those who have made “contributions of unusual distinction” to the field of labor economics.

Among these contributions are Kramarz’s work with John Abowd (Cornell and Census) and Margolis (Paris I, CNRS) for the analysis of Linked Employer-Employee data and the so-called AKM model of compensation. This line of research has had an important impact on labor economics as well as fields where bipartite graphs are analyzed (students and schools, patients and hospitals…). Kramarz was also a pioneer in connecting labor markets outcomes with product market competition, including international trade, or in the study of the French minimum wage.

“I am honored to be elected a fellow of the Society of Labor Economists,” Kramarz said. “It is particularly significant to be recognized by the leaders in one’s primary field of research, the existing fellows of the Society.” Indeed, Kramarz is the second French labor economist to receive this distinction (with P.A. Chiappori being the first).

Kramarz, along with Professor Alexandre Mas (Princeton University), was elected by the current SOLE fellows for their career achievements, and their election was announced in the plenary session of the 2019 SOLE Meetings on May 3 in Arlington, Va.

For more information click here.

Workshop on Political Economy

CREST – Ecole Polytechnique – ENSAE
April 4, 2019
Workshop on Political Economy

Organizers: Pierre Boyer, Yukio Koriyama, Alessandro Riboni and Clémence Tricaud
Address: CREST 5, avenue Henry Le Chatelier 91120 Palaiseau, How to come?
Rooms: 1002 & 1003 (first floor)

9:30 Welcome Coffee

10:00-10h45 Quoc Anh Do (Sciences Po): “Friendship Networks and Political Opinions: A Natural Experiment among Future French Politicians”, with Yann Algan, Nicolò Dalvit, and Yves Zenou

10:45-11h30 Ekaterina Zhuravskaya (PSE): “Diffusion of Gender Norms: Evidence from Stalin’s Ethnic Deportations”, with Alain Blum and Alexandra Jarotschkin

11:30-11:45 Coffee break

11:45-12h30 Clémence Tricaud (CREST): “Better Alone? Evidence on the costs of intermunicipal cooperation”

12:30-13h15 Marc Sangnier (AMSE): “Political connections and insider trading” with Thomas Bourveau and Renaud Coulomb

13:15-14:15 Lunch break

14:15-15:00 Benjamin Marx (Sciences Po): “Revolving Door MPs: Politician Turnover and Failed Accountability in Africa”

15:00-15h45 Yukio Koriyama (CREST): “The winner-take-all dilemma” with Kazuya Kikuchi

15:45-16:00 Coffee break

16:00-16:45 Allan Drazen (University of Maryland): “Reciprocity versus Reelection: Theory and Experiment”, with Prateik Dalmia and Erkut Ozbay

End of the Workshop

List of participants
Laurent Bach (ESSEC)
Guidogiorgio Bodrato (CREST)
Pierre Boyer (CREST)
Julia Cagé (Sciences Po)
Micael Castanheira (ECARES)
Gwen-Jiro Clochard (CREST)
Pierre-Edouard Collignon (CREST)
Sébastien Courtin (U Caen)
Allan Drazen (University of Maryland)
Quoc-Anh Do (Sciences Po)
Brice Fabre (PSE-IPP)
Germain Gauthier (CREST)
Jean-Michel Grandmont (CREST)
Daniel Hernández (CREST)
Helios Herrera (Warwick University)
Yukio Koriyama (CREST)
Quentin Lippmann (PSE)
Paul Maarek (U Panthéon Assas)
Benjamin Marx (Sciences Po)
Mickael Melki (Paris School of Business)
Matias Nunez (U Paris Dauphine)
Alessandro Riboni (CREST)
Marc Sangnier (AMSE)
Emilie Sartre (CREST)
Clémence Tricaud (CREST)
Alain Trognon (CREST)
Ekaterina Zhuravskaya (PSE)

You could download the program here.

Anna Simoni – Médaille de bronze du CNRS 2019

Anna Simoni, Chercheuse en économie, a reçu la médaille de bronze* du CNRS 2019.​
Vous pouvez trouver la liste des médailles 2019 ici.

* La Médaille de bronze récompense le premier travail d’un chercheur ou enseignant-chercheur prometteur dans son domaine.

Theoretical results for deep neural networks

Theoretical results for deep neural networks

Johannes Schmidt-Hieber
Leiden University

 

SCHEDULE Monday 14th January 2019
21st January 2019		 De 14h à 16h30 Salle 2016
Thursday 17th January 2019
24th January 2019		 De 14h à 16h30 Salle 2016


Theoretical results for deep neural networks

Summary:

Large databases and increasing computational power have recently resulted in astonishing performances of deep neural networks for a broad range of extremely complex tasks, including image and text classification, speech recognition and game playing. These deep learning methods are build by imitating the action of the brain and there are few theoretical results as of yet. To formulate a sound mathematical framework explaining these successes is a major challenge for current research.

The course aims to give an overview about existing theory for deep neural networks with a strong emphasis on recent developments. Core topics are approximation theory and complexity bounds for the function spaces generated by deep networks. Beyond that we also discuss modelling aspects, theoretical results on the energy landscape and statistical risk bounds.

Literature:

– Anthony, M., and Bartlett, P. L. Neural network learning: theoretical foundations. Cambridge University Press, 1999.
– Bach, F. Breaking the curse of dimensionality with convex neural networks. JMLR. 2017.
– Barron, A. Universal approximation bounds for superpositions of a sigmoidal function. IEEE . 1993.
– Barron, A. Approximation and estimation bounds for artificial neural networks. Machine Learning. 1994.
– Choromanska, A., Henaff, M., Mathieu, M., Arous, G. B., LeCun, Y. The loss surface of multilayer networks. Aistats. 2015.
– Goodfellow, Bengio, Courville. Deep Learning. MIT Press, 2016.
– Pinkus, A. Approximation theory of the MLP model in neural networks. Acta Numerica, 143-195, 1999.
– Schmidt-Hieber, J. Nonparametric regression using deep neural networks with ReLU activation function. ArXiv 2017.
– Telgarsky, M. Benefits of depth in neural networks. ArXiv. 2016.
– Yarotsky, D. Error bounds for approximations with deep ReLU networks. Neural Networks. 2017.