AI RESEARCH
Stability and Generalization for Decentralized Markov SGD
arXiv CS.LG
•
ArXi:2605.01701v1 Announce Type: new Stochastic gradient methods are central to large-scale learning, yet their generalization theory typically relies on independent sampling assumptions. In many practical applications, data are generated by Marko chains and learning is performed in a decentralized manner, which