no code implementations • NeurIPS 2020 • Clement Calauzenes, Nicolas Usunier
We provide an answer to this question in the form of a structural characterization of ranking losses for which a suitable regression is consistent.
no code implementations • 21 Jun 2019 • Syrine Krichene, Mike Gartrell, Clement Calauzenes
For example, applying constraints a posteriori can result in incomplete recommendations or low-quality results for the tail of the distribution (i. e., less popular items).
no code implementations • 31 Jan 2019 • Louis Faury, Clement Calauzenes, Olivier Fercoq, Syrine Krichen
Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions.