The laboratory staff submitted 3 articles to the NeurIPS 2023 conference:

1) Alexander Beznosikov, Alexander Gasnikov. Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities;

2) Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova, Alexander Gasnikov, Alexey Naumov, Eric Moulines. First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities;

3) Nikita Kornilov, Ohad Shamir, Aleksandr Lobanov, Alexander Gasnikov, Innokentiy Shibaev, Eduard Gorbunov, Darina Dvinskikh, Samuel Horváth.  Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance.

The conference is dedicated to fostering the exchange of research advances in Artificial Intelligence and Machine Learning. It includes invited talks, demonstrations, symposia, and oral and poster presentations of refereed papers. Along with the conference, thematic seminars are held.