Corpus ID: 211204922

Second-order Conditional Gradients

@article{Carderera2020SecondorderCG,
  title={Second-order Conditional Gradients},
  author={Alejandro Carderera and Sebastian Pokutta},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.08907}
}
Constrained second-order convex optimization algorithms are the method of choice when a high accuracy solution to a problem is needed, due to the quadratic convergence rates these methods enjoy when close to the optimum. These algorithms require the solution of a constrained quadratic subproblem at every iteration. In the case where the feasible region can only be accessed efficiently through a linear optimization oracle, and computing first-order information about the function, although… Expand
3 Citations
Convex optimization based on global lower second-order models
  • 3
  • PDF
Practical Frank-Wolfe algorithms
  • 1
  • PDF

References

SHOWING 1-10 OF 48 REFERENCES
Optimizing Costly Functions with Simple Constraints: A Limited-Memory Projected Quasi-Newton Algorithm
  • 233
  • Highly Influential
  • PDF
Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients
  • 25
  • Highly Influential
  • PDF
Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems
  • 9
  • Highly Influential
  • PDF
Polyak Steps for Adaptive Fast Gradient Method
  • 2
  • PDF
Model Function Based Conditional Gradient Method with Armijo-like Line Search
  • 3
  • PDF
Proximal quasi-Newton methods for regularized convex optimization with linear and accelerated sublinear convergence rates
  • 16
Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes
  • 32
  • PDF
Practical inexact proximal quasi-Newton method with global complexity analysis
  • 59
  • PDF
Cubic regularization of Newton method and its global performance
  • 607
  • PDF
On the Global Linear Convergence of Frank-Wolfe Optimization Variants
  • 256
  • PDF
...
1
2
3
4
5
...