AI RESEARCH
Massive Redundancy in Gradient Transport Enables Sparse Online Learning
arXiv CS.LG
•
ArXi:2603.15195v1 Announce Type: new Real-time recurrent learning (RTRL) computes exact online gradients by propagating a Jacobian tensor forward through recurrent dynamics, but at O(n^4) cost per step. Prior work has sought structured approximations (rank-1 compression, graph-based sparsity, Kronecker factorization