First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities

no code implementations • NeurIPS 2023 • Aleksandr Beznosikov, Sergey Samsonov, Marina Sheshukova, Alexander Gasnikov, Alexey Naumov, Eric Moulines

We present a unified approach for the theoretical analysis of first-order gradient methods for stochastic optimization and variational inequalities.

Stochastic Optimization

Rosenthal-type inequalities for linear statistics of Markov chains

no code implementations • 10 Mar 2023 • Alain Durmus, Eric Moulines, Alexey Naumov, Sergey Samsonov, Marina Sheshukova

In this paper, we establish novel deviation bounds for additive functionals of geometrically ergodic Markov chains similar to Rosenthal and Bernstein inequalities for sums of independent random variables.

Vocal Bursts Type Prediction