Corpus ID: 221802753

Affine-invariant contracting-point methods for Convex Optimization

@article{Doikov2020AffineinvariantCM,
  title={Affine-invariant contracting-point methods for Convex Optimization},
  author={Nikita Doikov and Y. Nesterov},
  journal={arXiv: Optimization and Control},
  year={2020}
}
In this paper, we develop new affine-invariant algorithms for solving composite con- vex minimization problems with bounded domain. We present a general framework of Contracting-Point methods, which solve at each iteration an auxiliary subproblem re- stricting the smooth part of the objective function onto contraction of the initial domain. This framework provides us with a systematic way for developing optimization methods of different order, endowed with the global complexity bounds. We show… Expand
1 Citations

Figures from this paper

Optimization Methods for Fully Composite Problems
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 minimizationExpand

References

SHOWING 1-10 OF 27 REFERENCES
Implementable tensor methods in unconstrained convex optimization
  • Y. Nesterov
  • Mathematics, Computer Science
  • Math. Program.
  • 2021
TLDR
New tensor methods for unconstrained convex optimization, which solve at each iteration an auxiliary problem of minimizing convex multivariate polynomial, and an efficient technique for solving the auxiliary problem, based on the recently developed relative smoothness condition are developed. Expand
Inexact accelerated high-order proximal-point methods
In this paper, we present a new framework of Bi-Level Unconstrained Minimization (BLUM) for development of accelerated methods in Convex Programming. These methods use approximations of theExpand
Optimal Combination of Tensor Optimization Methods
TLDR
A general framework allowing to obtain near-optimal oracle complexity for each function in the sum separately is proposed, meaning, in particular, that the oracle for a function with lower Lipschitz constant is called a smaller number of times. Expand
Gradient methods for minimizing composite functions
  • Y. Nesterov
  • Mathematics, Computer Science
  • Math. Program.
  • 2013
In this paper we analyze several new methods for solving optimization problems with the objective function formed as a sum of two terms: one is smooth and given by a black-box oracle, and another isExpand
Inexact Tensor Methods with Dynamic Accuracies
TLDR
This paper presents computational results on a variety of machine learning problems for several methods and different accuracy policies, and proposes two dynamic strategies for choosing the inner accuracy of inexact Tensor Methods for solving convex optimization problems with composite objective. Expand
A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications
TLDR
A framework which allows to circumvent the intricate question of Lipschitz continuity of gradients by using an elegant and easy to check convexity condition which captures the geometry of the constraints is introduced. Expand
Superfast second-order methods for unconstrained convex optimization
In this paper, we present new second-order methods with converge rate O(k^{-4}), where k is the iteration counter. This is faster that athe existing lower bound for this type of schemes [1,2], whichExpand
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
TLDR
A new general framework for convex optimization over matrix factorizations, where every Frank-Wolfe iteration will consist of a low-rank update, is presented, and the broad application areas of this approach are discussed. Expand
Complexity bounds for primal-dual methods minimizing the model of objective function
  • Y. Nesterov
  • Mathematics, Computer Science
  • Math. Program.
  • 2018
TLDR
This work provides Frank–Wolfe method with a convergence analysis allowing to approach a primal-dual solution of convex optimization problem with composite objective function and justifies a new variant of this method, which can be seen as a trust-region scheme applying to the linear model of objective function. Expand
Interior-point polynomial algorithms in convex programming
TLDR
This book describes the first unified theory of polynomial-time interior-point methods, and describes several of the new algorithms described, e.g., the projective method, which have been implemented, tested on "real world" problems, and found to be extremely efficient in practice. Expand
...
1
2
3
...