# Optimization Methods for Fully Composite Problems

@inproceedings{Doikov2021OptimizationMF, title={Optimization Methods for Fully Composite Problems}, author={Nikita Doikov and Y. Nesterov}, year={2021} }

In this paper, we propose a new Fully Composite Formulation of convex optimization problems. It includes, as a particular case, the problems with functional constraints, max-type minimization problems, and problems of Composite Minimization, where the objective can have simple nondifferentiable components. We treat all these formulations in a unified way, highlighting the existence of very natural optimization schemes of different order. We prove the global convergence rates for our methods… Expand

#### References

SHOWING 1-10 OF 29 REFERENCES

Gradient methods for minimizing composite functions

- Mathematics, Computer Science
- Math. Program.
- 2013

Regularized Newton Methods for Minimizing Functions with Hölder Continuous Hessians

- Mathematics, Computer Science
- SIAM J. Optim.
- 2017

Complexity bounds for primal-dual methods minimizing the model of objective function

- Mathematics, Computer Science
- Math. Program.
- 2018

Cubic regularization of Newton method and its global performance

- Mathematics, Computer Science
- Math. Program.
- 2006

An Accelerated Hybrid Proximal Extragradient Method for Convex Optimization and Its Implications to Second-Order Methods

- Mathematics, Computer Science
- SIAM J. Optim.
- 2013

Oracle complexity of second-order methods for smooth convex optimization

- Mathematics, Computer Science
- Math. Program.
- 2019

Implementable tensor methods in unconstrained convex optimization

- Mathematics, Computer Science
- Math. Program.
- 2021

Affine-invariant contracting-point methods for Convex Optimization

- Computer Science, Mathematics
- 2020

Minimizing Uniformly Convex Functions by Cubic Regularization of Newton Method

- Mathematics, Computer Science
- J. Optim. Theory Appl.
- 2021

An Optimal High-Order Tensor Method for Convex Optimization

- Mathematics, Computer Science
- COLT
- 2019