Sampling of semiorthogonal matrices for the Muon algorithm

DOI10.1134/S1064562425700565MaRDI QIDQ7295055zbMATH OpenFDO

Authors E. D. Petrov, G. V. Evseev, A. V. Antonov, A. S. Veprikov, N. A. Bushkov, S. V. Moiseev, Aleksandr Beznosikov

Publication date 13 July 2026

Published in Doklady Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/S1064562425700565

Mathematics Subject Classification ID

Natural language processing (68T50) Stochastic programming (90C15) Derivative-free methods and methods using generalized derivatives (90C56)

Cites work

• Backpropagation and stochastic gradient descent method
• Online convex optimization in the bandit setting: gradient descent without a gradient
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Zero order algorithm for decentralized optimization problems
• Zeroth-order optimization with orthogonal random directions

This page was built for publication: Sampling of semiorthogonal matrices for the Muon algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7295055)