RESIST: Resilient Decentralized Learning Using Consensus Gradient Descent

ArXi:2502.07977v2 Announce Type: replace Empirical risk minimization (ERM) is a cornerstone of modern machine learning (ML), ed by advances in optimization theory that ensure efficient solutions with provable algorithmic and statistical learning rates. Privacy, memory, computation, and communication constraints necessitate data collection, processing, and storage across network-connected devices. In many applications, networks operate in decentralized settings where a central server cannot be assumed, requiring decentralized ML algorithms that are efficient and resilient.