Adagrad

Complexity of Adagrad and other first-order methods for nonconvex optimization problems with bounds constraints

  • Serge Gratton
  • Sadok Jerad
  • Philippe L. Toint
    • Categories Bound-constrained Optimization, Data Science Algorithms, Nonlinear Optimization Tags , , , , ,

    A parametric class of trust-region algorithms for constrained nonconvex optimization is analyzed, where the objective function is never computed. By defining appropriate first-order stationarity criteria, we are able to extend the Adagrad method to the newly considered problem and retrieve the standard complexity rate of the projected gradient method that uses both the gradient and … Read more

    OFFO minimization algorithms for second-order optimality and their complexity

  • Serge Gratton
  • Philippe L. Toint
    • Categories Unconstrained Optimization Tags , , , ,

    An Adagrad-inspired class of algorithms for smooth unconstrained optimization is presented in which the objective function is never evaluated and yet the gradient norms decrease at least as fast as O(1/\sqrt{k+1}) while second-order optimality measures converge to zero at least as fast as O(1/(k+1)^{1/3}). This latter rate of convergence is shown to be essentially sharp … Read more

    Parametric complexity analysis for a class of first-order Adagrad-like algorithms

  • Serge Gratton
  • Sadok Jerad
  • Philippe L. Toint
    • Categories Stochastic Programming, Unconstrained Optimization Tags , , , , ,

    A class of algorithms for optimization in the presence of noise is presented, that does not require the evaluation of the objective function. This class generalizes the well-known Adagrad method. The complexity of this class is then analyzed as a function of its parameters, and it is shown that some methods of the class enjoy … Read more

    First-Order Objective-Function-Free Optimization Algorithms and Their Complexity

  • Serge Gratton
  • Sadok Jerad
  • Philippe L. Toint
    • Categories Unconstrained Optimization Tags , , , , ,

    A class of algorithms for unconstrained nonconvex optimization is considered where the value of the objective function is never computed. The class contains a deterministic version of the first-order Adagrad method typically used for minimization of noisy function, but also allows the use of second-order information when available. The rate of convergence of methods in … Read more