A restart-free accelerated algorithm for nonconvex minimization: continuous- and discrete-time analysis

We propose two deterministic momentum-based first-order methods for minimizing lower-bounded nonconvex functions with Lipschitz-continuous gradients and Hessians. Both methods attain an $\varepsilon$-approximate first-order stationary point in $O(\varepsilon^{-7/4})$ function and gradient evaluation