Corpus ID: 173991043

Towards Unified Acceleration of High-Order Algorithms under Hölder Continuity and Uniform Convexity

@article{Song2019TowardsUA,
  title={Towards Unified Acceleration of High-Order Algorithms under H{\"o}lder Continuity and Uniform Convexity},
  author={Chaobing Song and Y. Ma},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.00582}
}
  • Chaobing Song, Y. Ma
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • In this paper, through a very intuitive vanilla proximal method perspective, we derive accelerated high-order optimization algorithms for minimizing a convex function that has Holder continuous derivatives. In this general convex setting, we propose a concise unified acceleration framework (UAF), which reconciles the two different high-order acceleration approaches, one by Nesterov and Baes [29, 3, 33] and one by Monteiro and Svaiter [25]. As result, the UAF unifies the high-order acceleration… CONTINUE READING
    13 Citations
    Inexact Tensor Methods with Dynamic Accuracies
    • 3
    • PDF
    Optimal Combination of Tensor Optimization Methods
    • 8
    • PDF
    Local convergence of tensor methods
    • 7
    • PDF
    A Control-Theoretic Perspective on Optimal High-Order Optimization
    • 3
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 51 REFERENCES
    Accelerated Extra-Gradient Descent: A Novel Accelerated First-Order Method
    • 26
    • Highly Influential
    • PDF
    Implementable tensor methods in unconstrained convex optimization
    • Y. Nesterov
    • Mathematics, Computer Science
    • Math. Program.
    • 2021
    • 53
    • Highly Influential
    • PDF
    An Accelerated Hybrid Proximal Extragradient Method for Convex Optimization and Its Implications to Second-Order Methods
    • 81
    • Highly Influential
    • PDF
    A Universal Primal-Dual Convex Optimization Framework
    • 51
    • PDF
    An Optimal High-Order Tensor Method for Convex Optimization
    • 24
    • Highly Influential
    • PDF
    Sub-sampled Cubic Regularization for Non-convex Optimization
    • 73
    • PDF
    The Approximate Duality Gap Technique: A Unified Theory of First-Order Methods
    • 38
    • Highly Influential
    • PDF
    Complexity bounds for primal-dual methods minimizing the model of objective function
    • Y. Nesterov
    • Mathematics, Computer Science
    • Math. Program.
    • 2018
    • 56
    • PDF
    Universal Regularization Methods: Varying the Power, the Smoothness and the Accuracy
    • 27
    • PDF
    Estimate sequence methods: extensions and approximations
    • 74
    • Highly Influential
    • PDF