technique
Lyapunov function
techniqueactiveprovisional
lyapunov-function-d4181022·1 events·first seen 16d agoAliases: Lyapunov function
Co-occurring entities
More like this (12)
Laplace KernelL-infinity perturbationLog-Sobolev InequalityLangevin DynamicsPolyak–Łojasiewicz ConditionForward Euler ODEbirth-death Langevin dynamicsOrnstein-Uhlenbeck stochastic differential equationKullback-Leibler divergenceSDE (Stochastic Differential Equation LR scaling)Neural Ordinary Differential Equationslatent dynamical systems
Recent events (1)
Tight Convergence Theory for Error Feedback Algorithms in Distributed Optimization
This paper provides tight convergence analyses for two major error-feedback algorithms—classic Error Feedback (EF) and Error Feedback 21 (EF21)—used to mitigate communication bottlenecks in distributed learning. The authors identify optimal step-size choices and construct tailored Lyapunov functions for each method, yielding guarantees that hold independently of the number of agents and recover the best known single-agent bounds. The work clarifies the relative performance of these gradient compression variants, which has remained poorly understood despite widespread use.