×
Jul 23, 2019 · In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points? The answer is yes!
Theoretically, we prove that heavy-ball gradient descent enjoys larger stepsize than the gradient descent to escape saddle points to escape the saddle point.
Theoretically, it is proved that heavy-ball gradient descent enjoys larger stepsize than the gradient descent to escape saddle points to escape the saddle ...
Theoretically, we prove that heavy-ball gradient descent enjoys larger stepsize than the gradient descent to escape saddle points to escape the saddle point.
People also ask
In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points? The answer is yes! Direct using the ...
Theoretically, we prove that heavy-ball gradient descent enjoys larger stepsize than the gradient descent to escape saddle points to escape the saddle point.
This paper develops a new perturbation mechanism for optimization algorithms. In this mechanism, perturbations are adapted to the history of states via the ...
Heavy ball method: The heavy ball method was originally proposed by Polyak (1964). It has been observed that this algorithm, even in the deterministic setting, ...
Jun 4, 2024 · I.: Accelerated gradient descent escapes saddle points faster than gradient descent. In: S. Bubeck, V. Perchet, and P. Rigollet (eds ...