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 20 of 155 for “"Convergence Guarantees"”.

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

    … with the extragradient method. We establish convergence guarantees for PEARL-EG for both strongly monotone and monotone problems, explain its benefits over prior approaches, and present numerical experiments that complement the theory by exploring practical performance and limitations.

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

  2. Fixed-Time Reinforcement Learning-based Control for Safe Autonomy

    … safe learning architectures lack finite time convergence guarantees, rendering these algorithms impractical for real-world applications. In this dissertation, we enable safe autonomy by endowing autonomous systems with safety-critical control frameworks predicated on online reinforcement …

    gatech Repository record for Fixed-Time Reinforcement Learning-based Control for Safe Autonomy (opens in a new tab)

  3. FINITE-TIME CONVERGENCE ANALYSIS OF ACTOR-CRITIC ALGORITHMS

    … In the thesis, we provide the first global convergence guarantees for two-timescale actor-critic (AC) on linear quadratic regulator (LQR) problems, achieving epsilon-optimality with provable sample complexity. These results are generalized to Markov Decision Processes (MDPs) and extended to …

    nus Repository record for FINITE-TIME CONVERGENCE ANALYSIS OF ACTOR-CRITIC ALGORITHMS (opens in a new tab) Download file for FINITE-TIME CONVERGENCE ANALYSIS OF ACTOR-CRITIC ALGORITHMS (opens in a new tab)

  4. Optimisation and computational optimal control via local pursuit

    … to noise-free non-stationary ones, preserving convergence guarantees and matching the quality of the ‘full-knowledge’ benchmark approach at substantially lower computational cost. Subsequently, we account for noise in both agent and obstacle observations, where convergence guarantees are …

    greece Repository record for Optimisation and computational optimal control via local pursuit (opens in a new tab)

  5. Reinforcement learning for multi-agent and robust control systems

    … for these settings, supported by theoretical convergence guarantees. In setting i, a team of collaborative MARL agents is connected via a communication network, without the coordination of any central controller. With only neighbor-to-neighbor communications, we introduce decentralized …

    uiuc Repository record for Reinforcement learning for multi-agent and robust control systems (opens in a new tab)

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

    … 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 capture the operators encountered in many modern …

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

  7. Factoring over probability simplices : from theory to applications

    … we establish subsequential and full-sequence convergence guarantees. This analysis framework proves remarkably versatile: we successfully apply it to both our probabilistic tensor factorization models and to an adaptive graph-regularized denoising method for spatial transcriptomics, where the …

    ubc Repository record for Factoring over probability simplices : from theory to applications (opens in a new tab) Download PDF for Factoring over probability simplices : from theory to applications (opens in a new tab)

  8. Regret minimisation and system-efficiency in route choice

    … objective a moving target. As a side effect, no convergence guarantees exist for the general MARL setting. This thesis exploits a particular MARL problem, namely route choice (where selfish drivers aim at choosing routes that minimise their travel costs), to deliver convergence guarantees. We are …

    brazil-ufrgs Repository record for Regret minimisation and system-efficiency in route choice (opens in a new tab)

  9. Dynamic Algorithms and Asymptotic Theory for Lp-norm Data Analysis

    … (SVD), and asymptotic convergence guarantees. However, PCA has been shown to be highly sensitive to faulty measurements (outliers) because of its reliance on the outlier-sensitive L2-norm. Arguably, the most straightforward approach to impart robustness against outliers …

    rit Repository record for Dynamic Algorithms and Asymptotic Theory for Lp-norm Data Analysis (opens in a new tab)

  10. Faster Conditional Gradient Algorithms for Machine Learning

    … either locally or globally improve upon existing convergence guarantees. In Chapters 2-4 we focus on the case where the objective function is smooth and strongly convex and the feasible region is a polytope, and in Chapter 5 we focus on the case where the function is generalized self-concordant …

    gatech Repository record for Faster Conditional Gradient Algorithms for Machine Learning (opens in a new tab)

  11. Nonconvex Optimization Methods with Applications to Portfolio Selection and Hybrid Systems

    … and develop efficient algorithms with standard convergence guarantees. The effectiveness of the algorithms is demonstrated in detail for both applications with numerical experiments.

    washington Repository record for Nonconvex Optimization Methods with Applications to Portfolio Selection and Hybrid Systems (opens in a new tab)

  12. Algorithms and Theory for Saddle Point Problems with Relaxed Structural Conditions

    … show that our proposed method achieves a linear convergence rate under either condition. These results extend linear convergence guarantees beyond the strong convexity--strong concavity setting typically required in existing analyses. The second research chapter of this dissertation studies …

    arizona-thes Repository record for Algorithms and Theory for Saddle Point Problems with Relaxed Structural Conditions (opens in a new tab)

  13. GRADIENT DESCENT METHODS IN MODERN MACHINE LEARNING PROBLEMS: PROVABLE GUARANTEES

    … is non-convex and non-smooth, the standard convergence guarantees of GD for convex loss functions cannot be applied. Instead, through a kernel perspective, we demonstrate that when fresh data arrives in a stream, SGD ensures the exponential convergence of the average prediction error. In the …

    duke Repository record for GRADIENT DESCENT METHODS IN MODERN MACHINE LEARNING PROBLEMS: PROVABLE GUARANTEES (opens in a new tab)

  14. Projection-Free and Accelerated Methods for Constrained Optimization and Saddle-Points Problems

    … offering robust solutions with theoretical guarantees. In the first part of the dissertation, we propose an inexact-proximal accelerated gradient method to address nonconvex stochastic composite optimization problems, where the objective function is composed of smooth and nonsmooth …

    arizona-thes Repository record for Projection-Free and Accelerated Methods for Constrained Optimization and Saddle-Points Problems (opens in a new tab)

  15. BUILDING AND MAINTAINING STRUCTURE IN DISTRIBUTED NETWORKS

    … a tight analysis of tolerable churn and recovery guarantees against catastrophic failures like denial-of-service attacks. Finally, the thesis explores self-stabilizing overlay networks through graph linearization augmented with untrusted advice. This mechanism achieves optimal self-stabilization …

    nus Repository record for BUILDING AND MAINTAINING STRUCTURE IN DISTRIBUTED NETWORKS (opens in a new tab) Download file for BUILDING AND MAINTAINING STRUCTURE IN DISTRIBUTED NETWORKS (opens in a new tab)

  16. Efficient Hierarchical Global Motion Planning for Autonomous Vehicles

    … non-trivial, including issues such as algorithm convergence, its correspondence to system controllability, optimality of solution, computational complexity, and dynamic environments. In response to these challenges, a hierarchical algorithm will be introduced that provides (a) decreased …

    uiuc Repository record for Efficient Hierarchical Global Motion Planning for Autonomous Vehicles (opens in a new tab)

  17. Across the Reinforcement Learning and Large Language Model Spectrum

    … The first part develops rigorous theoretical guarantees for RL on tabular Markov decision processes (MDPs), specifically, variance-dependent regrets for MDPs and latent MDPs, and a fundamental progress on completely horizon-free regrets. The second part studies how language models retrieve …

    washington Repository record for Across the Reinforcement Learning and Large Language Model Spectrum (opens in a new tab)

  18. SOME PRIMAL-DUAL THEORY FOR SUBGRADIENT METHODS FOR STRONGLY CONVEX OPTIMIZATION

    … method. These equivalences enable optimal convergence guarantees in terms of both their classic primal gap and a not previously analyzed dual gap for strongly convex optimization. Consequently, our theory provides these classic methods with simple, optimal stopping criteria and optimality …

    jhu Repository record for SOME PRIMAL-DUAL THEORY FOR SUBGRADIENT METHODS FOR STRONGLY CONVEX OPTIMIZATION (opens in a new tab)

Page 1 of 8