Jump to navigation
Nicolo Cesa-Bianchi, Tommaso Cesari, Yishay Mansour et Vianney Perchet
2021
We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our setting is motivated by the use case of companies that regularly receive proposals for technological innovations and want to quickly decide whether they are worth implementing. We...
Nicolo Cesa-Bianchi, Tommaso Cesari, Roberto Colomboni, Federico Fusco et Stefano Leonardi
Jérôme Bolte, Tam Le, Edouard Pauwels et Antonio Silveti-Falls
sous la direction de M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang et J. Wortman Vaughan, 2021, révision 10 juin 2026, p. 13537–13549
In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) provided that a nonsmooth form of the classical invertibility condition is...
Sara Pisani, Jennifer Murphy, Jane Conway, Edward Millgate, Caroline Catmur et Geoffrey Bird
vol. 131, décembre 2021, p. 497–524
Theory of Mind (ToM), the ability to represent the mental states of oneself and others, is an essential social skill disrupted across many psychiatric conditions. The transdiagnostic nature of ToM impairment means it is plausible that ToM impairment is related to alexithymia (difficulties...
Sandeep Bhupatiraju et Daniel L. Chen
vol. 33, n° 2, 2021
Artificial Intelligence (‘AI’) and machine learning (‘ML’) — adaptive computer programs that attempt to perform functions typically associated with the human mind — offer new opportunities for improving the decision-making capacity and productivity of the Indian judiciary. First, the algorithmic...
Christian Gollier
sous la direction de Francesco Caselli, Rick van der Ploeg et Alexander Ludwig, CEPR, 2021
J. Simoes, D. Moran, S. Edwards, Céline Bonnet, A. Lopez-Sebastian et P. Chemineau
vol. 15, n° 1, décembre 2021
Stephan Seiler
Online, 2021, révision 10 juin 2026
Koléhè Coulibaly-Pasquier et Laurent Miclo
n° 171, 2021, 110 pages
On a manifold, consider an elliptic diffusion X admitting an invariant measure μ. The goal of this paper is to introduce and investigate the first properties of stochastic domain evolutions (Dt)t∈[0,τ] which are intertwining dual processes for X (where τ is an appropriate positive stopping time...
Manh-Hung Nguyen
vol. Chaper 5, 2021
