Aller au contenu principal

Aleksandra Burashnikova

Mercredi 6 Juillet 2022

Large-Scale Sequential Learning for Recommender and Engineering Systems


In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. To demonstrate the empirical efficiency of the proposed approaches we investigate their  applications for decision making in recommender systems and energy systems domains.

For the former, we propose novel algorithm called SAROS that take into account both kinds of feedback for learning over the sequence of interactions. The proposed approach consists in minimizing pairwise ranking loss over blocks constituted by a sequence of non-clicked items followed by the clicked one for each user. We also explore the influence of long memory on the accurateness of predictions. SAROS shows highly competitive and promising results based on quality metrics and also it turn out faster in terms of loss convergence than stochastic gradient descent and batch classical approaches.

Regarding power systems, we propose an algorithm for faulted lines detection based on focusing of misclassifications in lines close to the true event location. The proposed idea of taking into account the neighbour lines shows statistically significant results in comparison with the initial approach based on convolutional neural networks for faults detection in power grid.

Date et Lieu

Mercredi 6 Juillet 2022 à 15h30
à Skoltech
et Click here to join the meeting


Massih-Reza AMINI



Composition du jury

Professeur et Institut de Physique et de Technologie de Moscou, Rapporteur
Vincent GUIGUE
Professeur associé et Université Pierre et Marie Curie, Rapporteur
Professeur et Institut des Sciences et de la Technologie de Skolkovo, Examinateur
Professeur et l’Université Grenoble Alpes, Président
Vladimir TERZIJA
Professeur et Institut des Sciences et de la Technologie de Skolkovo, Président

Publié le 30 juin 2022

Mis à jour le 30 juin 2022