Paper accelerates SAGA using sampled negative momentum.
problem Directly accelerating SAGA for optimization problems.
method Proposes SSNM for direct acceleration of SAGA.
result Achieves best known oracle complexity for strongly convex problems.
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper accelerates SAGA using sampled negative momentum.