Sehore, Feb. 17 -- day International Workshop titled "Numerical & Optimization Techniques for Machine Learning in Real-World Applications" from 11th to 13th February 2026, in online mode.
Abstract: This paper studies the distributed minimax optimization problem over networks. To enhance convergence performance, we propose a distributed optimistic gradient tracking method, termed DOGT, ...
Abstract: We propose the Adaptive Step-Size Coordinate Descent (AS-CD) algorithm for online convex optimization in dynamic environments. Unlike fixed step size methods, AS-CD adapts step sizes and ...