1.5k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Toulouse-I-CapitoleFR31 papers
- Centre National de la Recherche ScientifiqueFR29 papers
- Université Toulouse III - Paul SabatierFR26 papers
- Institut de Mathématiques de ToulouseFR25 papers
- Université de ToulouseFR24 papers
- Institut de Recherche en Informatique de ToulouseFR19 papers
- Toulouse School of Economics ResearchFR17 papers
- Institut National des Sciences Appliquées de ToulouseFR16 papers
- Université Toulouse CapitoleFR14 papers
- Technology Solutions Experts (United States)US13 papers
- Université Toulouse - Jean JaurèsFR11 papers
- Centre de Recherche en Économie et StatistiqueFR10 papers
165 papers
On-line Pick-Freeze Mirror algorithm for Sensitity Analysis
Manon Costa, Sébastien Gadat, Xavier Gendre +1
The main objective of this paper is to propose a new approach for estimating the entire collection of Sobol' indices simultaneously. Our approach exploits the fact that Sobol' indi…
Convergence of optimizers implies eigenvalues filtering at equilibrium
Jerome Bolte, Quoc-Tung Le, Edouard Pauwels
Ample empirical evidence in deep neural network training suggests that a variety of optimizers tend to find nearly global optima. In this article, we adopt the reversed perspective…
A class of singular control problems with tipping points
Jean-Paul Décamps, Fabien Gensbittel, Thomas Mariotti +1
Tipping points characterize situations where a regulated system may experience a sudden and irreversible change and are generally associated with a random state of the system below…
Public Communication with Externalities
Georgy Lukyanov, Konstantin Shamruk, Tong Su +1
This paper develops a model in which a sender strategically communicates with a group of receivers whose payoffs depend on the sender's information. It is shown that aggregate payo…
The Welfare Effects of Policy Signalling in a Regime Change Game
Georgy Lukyanov
We explore a specific parametric example of a regime change game in which a policymaker defends the status quo against a continuum of atomistic agents who seek to overthrow it. At…
Mixtures Closest to a Given Measure: A Semidefinite Programming Approach
Srećko Đurašinović, Jean-Bernard Lasserre, Victor Magron
Mixture models, such as Gaussian mixture models, are widely used in machine learning to represent complex data distributions. A key challenge, especially in high-dimensional settin…
Honesty, Stigma, and Cooperation in an Overlapping-Generations Game
David Li, Georgy Lukyanov
We study a two-period overlapping-generations game in which a young agent interacts with an old agent and carries a binary record into old age. Honest agents cooperate with clear p…
Costly Comparison and Informational Inertia
Georgy Lukyanov, Ariza Azova, Arina Azova
A price cut can attract consumers while changing what their purchases reveal to later buyers. We study this trade-off in a duopoly with common uncertainty about quality. Consumers…
The Science Fiction Science Method
Iyad Rahwan, Azim Shariff, Jean-François Bonnefon
Predicting the social and behavioral impact of future technologies, before they are achieved, would allow us to guide their development and regulation before these impacts get entr…
Diagnostic Feedback under Hidden Task Difficulty
Mark Izgarshev, Georgy Lukyanov
An assessment is meant to tell an agent about herself, but its purchase can reveal the task. An evaluator privately observes task difficulty and may publicly purchase an ability di…
Quality at Stale Prices
Georgy Lukyanov, Konstantin Shamruk, Ekaterina Logina
We study a continuous-time game in which a firm privately chooses quality and a public-information pricing desk revises its posted price at Poisson opportunities. Customers learn f…
Residual Prophet Inequalities
Jose Correa, Sebastian Perez-Salazar, Dana Pizarro +1
We introduce a variant of the classic prophet inequality, called \emph{residual prophet inequality} (RPI). In the RPI problem, we consider a finite sequence of nonnegative inde…
The Theory of Economic Complexity
César A. Hidalgo, Viktor Stojkoski
We provide a mechanistic foundation for economic complexity methods. In our model, an economy's ability to produce an activity depends on the joint presence of required capabilitie…
ICS for complex data with application to outlier detection for density data
Camille Mondon, Huong Thi Trinh, Anne Ruiz-Gazen +1
Invariant coordinate selection (ICS) is a dimension reduction method, used as a preliminary step for clustering and outlier detection. It has been primarily applied to multivariate…
Augmenting the availability of historical GDP per capita estimates through machine learning
Philipp Koch, Viktor Stojkoski, César A. Hidalgo
Can we use data on the biographies of historical figures to estimate the GDP per capita of countries and regions? Here we introduce a machine learning method to estimate the GDP pe…
Sample complexity of optimal transport barycenters with discrete support
Léo Portales, Edouard Pauwels, Elsa Cazelles
Computational implementation of optimal transport barycenters for a set of target probability measures requires a form of approximation, a widespread solution being empirical appro…
Shannon-and von neumann-entropy regularizations of linear and semidefinite programs
Saroj Prasad Chhatoi, Jean B Lasserre
We consider the LP in standard form min {c T x\,: Ax = b; x 0} and inspired by -regularization in Optimal Transport, we introduce its -regularization ''min {c T x + …
Inference in dynamic models for panel data using the moving block bootstrap
Ayden Higgins, Koen Jochmans
Inference in linear panel data models is complicated by the presence of fixed effects when (some of) the regressors are not strictly exogenous. Under asymptotics where the number o…
On the Private Estimation of Smooth Transport Maps
Clément Lalanne, Franck Iutzeler, Jean-Michel Loubes +1
Estimating optimal transport maps between two distributions from respective samples is an important element for many machine learning methods. To do so, rather than extending discr…
Convergence rate of Euler-Maruyama scheme for McKean-Vlasov SDEs with density-dependent drift
Anh-Dung Le
In this paper, we study weak well-posedness of a McKean-Vlasov stochastic differential equations (SDEs) whose drift is density-dependent and whose diffusion is constant. The existe…
A second-order-like optimizer with adaptive gradient scaling for deep learning
Jérôme Bolte, Ryan Boustany, Edouard Pauwels +1
In this empirical article, we introduce INNAprop, an optimization algorithm that combines the INNA method with the RMSprop adaptive gradient scaling. It leverages second-order info…
Privately Learning Smooth Distributions on the Hypercube by Projections
Clément Lalanne, Sébastien Gadat
Fueled by the ever-increasing need for statistics that guarantee the privacy of their training sets, this article studies the centrally-private estimation of Sobolev-smooth densiti…
Invariant Coordinate Selection and Fisher discriminant subspace beyond the case of two groups
Colombe Becquart, Aurore Archimbaud, Anne Ruiz-Gazen +2
Invariant Coordinate Selection (ICS) is a multivariate technique that relies on the simultaneous diagonalization of two scatter matrices. It serves various purposes, including its…
Constant Payoff Property in Zero-Sum Stochastic Games with a Finite Horizon
Thomas Ragel, Bruno Ziliotto
This paper examines finite zero-sum stochastic games and demonstrates that when the game's duration is sufficiently long, there exists a pair of approximately optimal strategies su…