Adaptive first-order methods in optimization have widespread ML applications due to their
ability to adapt to non-convex landscapes. However, their convergence guarantees are …

Adaptive algorithms like AdaGrad and AMSGrad are successful in nonconvex optimization
owing to their parameter-agnostic ability–requiring no a priori knowledge about problem …

We examine a flexible algorithmic framework for solving monotone variational inequalities in
the presence of randomness and uncertainty. The proposed template encompasses a wide …

Universal methods achieve optimal convergence rate guarantees in convex optimization
without any prior knowledge of the problem's regularity parameters or the attributes of the …

The classical AdaGrad method adapts the learning rate by dividing by the square root of a
sum of squared gradients. Because this sum on the denominator is increasing, the method …

The article is devoted to the development of numerical methods for solving variational
inequalities with relatively strongly monotone operators. We consider two classes of …

Universal methods for optimization are designed to achieve theoretically optimal
convergence rates without any prior knowledge of the problem's regularity parameters or the …

Настоящая статья посвящена некоторым адаптивным методам первого порядка для
оптимизационных задач с относительно сильно выпуклыми функционалами. Недавно …

The paper deals with a significant extension of the recently proposed class of relatively
strongly convex optimization problems in spaces of large dimension. In the present paper …

Several important problems in learning theory and data science involve high-dimensional
optimization objectives that transcend the standard Lipschitz regularity conditions. The …