Can I read Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness on EtoBox?

Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness by Agafonov, Artem; Kamzolov, Dmitry; Gasnikov, Alexander; Kavis, Ali; Antonakopoulos, Kimon; Cevher, Volkan; Takáč, Martin is a scholarly article available to read on EtoBox.

What is Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness about?

We present a new accelerated stochastic second-order method that is robust to both gradient and Hessian inexactness, which occurs typically in machine learning. We establish theoretical lower bounds and prove that our algorithm achieves optimal convergence in both gradient and Hessian inexactness in this key setting. We further introduce a tensor generalization for stochastic higher-order derivatives. When the oracles are non-stochastic, the proposed tensor algorithm matches the global convergence of Nesterov Accelerated Tensor method. Both algorithms allow for approximate solutions of their auxiliary subproblems with verifiable conditions on the accuracy of the solution.

Author

Agafonov, Artem; Kamzolov, Dmitry; Gasnikov, Alexander; Kavis, Ali; Antonakopoulos, Kimon; Cevher, Volkan; Takáč, Martin

Published

2023

Language

EN