Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 10 of 10 for “"Extragradient"”.

  1. Extragradient-type Methods for (L0, L1)-Lipschitz Variational Inequality Problems

    … using first-order iterative methods known as extragradient-type algorithms. Traditionally, the convergence of these algorithms has been analyzed under the L-Lipschitz assumption, but recent research has found that this assumption is often overly restrictive in practice and does not accurately …

    jhu Repository record for Extragradient-type Methods for (L0, L1)-Lipschitz Variational Inequality Problems (opens in a new tab)

  2. PER PLAYER LOCAL EXTRAGRADIENT IN MULTIPLAYER FEDERATED LEARNING: CONVERGENCE GUARANTEES AND PRACTICAL PERFORMANCE

    … objectives, aiming to reach an equilibrium. The extragradient method (EG) is one of the most popular and efficient algorithms for solving min-max problems and multiplayer games. In this thesis, we introduce Per-Player Local Extragradient (PEARL-EG), which adapts the classical EG method to the …

    jhu Repository record for PER PLAYER LOCAL EXTRAGRADIENT IN MULTIPLAYER FEDERATED LEARNING: CONVERGENCE GUARANTEES AND PRACTICAL PERFORMANCE (opens in a new tab)

  3. Learning and Optimization on Geodesic Metric Spaces

    … the last-iterate convergence of Riemannian extragradient-type methods, which can be provably employed to tackle Riemannian minimax problems. The result in Euclidean space, achieved by extragradient, is $O\left(\frac{1}{\sqrt{T}}\right)$. We propose Riemannian extragradient and Riemannian …

    gatech Repository record for Learning and Optimization on Geodesic Metric Spaces (opens in a new tab)

  4. Next-Generation Iterative Algorithms for Large-scale Min-max Optimization: Design and Analysis

    … Chapter 2 focuses on the single-call stochastic extragradient method called SPEG. Our analysis introduces the Expected Residual condition, leading to improved convergence guarantees for structured non-monotone root-finding problems under broad sampling schemes. Moreover, our work addresses …

    jhu Repository record for Next-Generation Iterative Algorithms for Large-scale Min-max Optimization: Design and Analysis (opens in a new tab)

  5. Iterative Methods for Stochastic Variational Inequalities

    … probabilistic distributions. We consider several extragradient methods for the solutions of the variational inequalities and compare their relative efficiency and eectiveness through thorough numerical comparisons. Several applications such as trac equilibrium, environmental games, and …

    rit Repository record for Iterative Methods for Stochastic Variational Inequalities (opens in a new tab)

  6. Accelerated algorithms for composite saddle-point problems and applications

    … to the block-decomposition hybrid proximal extragradient (BD-HPE) framework. The framework consists of a family of inexact proximal point methods for solving a general two-block structured monotone inclusion problem which, at every iteration, solves two prox sub-inclusions according to a …

    gatech Repository record for Accelerated algorithms for composite saddle-point problems and applications (opens in a new tab)

  7. EXPERIMENTAL EVALUATION OF ITERATIVE METHODS FOR GAMES

    … methods, such as gradient descent ascent (GDA), Extragradient (EG), and Hamiltonian Gradient Descent (HGD) are usually implemented to solve those problems. In large-scale setting, stochastic variants of those gradient methods are prefer because of their cheap per iteration cost. To further …

    jhu Repository record for EXPERIMENTAL EVALUATION OF ITERATIVE METHODS FOR GAMES (opens in a new tab)

  8. Iterative Methods for the Elasticity Imaging Inverse Problem

    … optimization methods, including gradient, extragradient, and proximal point methods, are explored and applied to solve the related optimization problem. Implementations of all of the iterative techniques under consideration are applied to all of the developed optimization frameworks using a …

    rit Repository record for Iterative Methods for the Elasticity Imaging Inverse Problem (opens in a new tab)

  9. Algorithmic, Structural, and Pragmatic Acceleration Techniques in Machine Learning and Quantum Computing

    … eigenvalue distribution where the momentum extragradient method exhibits accelerated convergence rates, along with the optimal hyperparameters for each scenario.

    rice Repository record for Algorithmic, Structural, and Pragmatic Acceleration Techniques in Machine Learning and Quantum Computing (opens in a new tab)

  10. Block-decomposition and accelerated gradient methods for large-scale convex optimization

    … choices of stepsizes for performing the extragradient step; and dynamic updates of scaled inner products to balance the blocks. Finally, computational results on several classes of SDPs are presented showing that the exact BD methods outperform the three most competitive codes for solving …

    gatech Repository record for Block-decomposition and accelerated gradient methods for large-scale convex optimization (opens in a new tab)