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 15 of 15 for “"Last-iterate"”.

  1. Last iterate convergence in network zero-sum games

    … in this generalization. We then generalize last iterate convergence results obtained previously in two-player zero-sum games. We analyze convergence rates when players update their strategies using Mirror Descent, and Optimistic Mirror Descent. We analyze these algorithms when they are used …

    ubc Repository record for Last iterate convergence in network zero-sum games (opens in a new tab) Download PDF for Last iterate convergence in network zero-sum games (opens in a new tab)

  2. Singular Diffusion Limit of Tagged Particle Dynamics in a 1 Dimensional Zero Range Process With Sinai-Type Medium and the Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes

    … is to compute the convergence rate for the last iterate of stochastic gradient descent schemes. With respect to these problems, this thesis is similar in presentation to [HLS25] and [Hud25] respectively, but we augment with details, motivations, and ideas in important parts. At the time of …

    arizona-thes Repository record for Singular Diffusion Limit of Tagged Particle Dynamics in a 1 Dimensional Zero Range Process With Sinai-Type Medium and the Convergence Rate for the Last Iterate of Stochastic Gradient Descent Schemes (opens in a new tab)

  3. Formal guarantees for heuristic optimization algorithms used in machine learning

    … to noise under PL condition. Third, we study the last iterate of momentum methods. We prove the first lower bound in the general convex setting for the last iterate of SGD with constant momentum. Based on the fact that the lower bound is suboptimal, we investigate a class of (both adaptive and …

    bu Repository record for Formal guarantees for heuristic optimization algorithms used in machine learning (opens in a new tab)

  4. Convergence in min-max optimization

    … by Karlin from 1959. We also show that linear last-iterate convergence rates are possible for the Hamiltonian Gradient Descent algorithm for the class of “sufficiently bilinear” min-max problems. Finally, we explore higher-order methods for min-max optimization and monotone variational …

    gatech Repository record for Convergence in min-max optimization (opens in a new tab)

  5. Across the Reinforcement Learning and Large Language Model Spectrum

    … online direct preference optimization (DPO) and last-iterate convergence guarantees for Nash learning under non-transitive preferences. The final part turns to RL for LLMs, presenting reflection-assisted online fine-tuning for agentic tasks, and a large-scale distributed RL post-training …

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

  6. Provably effective algorithms for min-max optimization

    … 2. Can projection-free algorithms achieve last-iterate convergence for constrained min-max optimization problems with the convex-concave landscape? 3. Can we show that stochastic gradient descent-ascent, a method commonly used in practice for GAN training, actually finds global optima and …

    texas Repository record for Provably effective algorithms for min-max optimization (opens in a new tab)

  7. Learning and Optimization on Geodesic Metric Spaces

    … to achieve sub-linear regret on manifolds. Lastly, we consider 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 …

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

  8. Enhancing optimization algorithms for non-convex settings : federated and decentralized learning

    In the last decade, the rise and unprecedented success of neural networks have drawn significant attention from the machine learning community to non-convex optimization. This thesis focuses on federated and decentralized learning within the framework of non-convex optimization, aiming to deepen …

    texas Repository record for Enhancing optimization algorithms for non-convex settings : federated and decentralized learning (opens in a new tab)

  9. OFFLINE REINFORCEMENT LEARNING FOR MDPS AND CONFOUNDED POMDPS: POLICY GRADIENT ALGORITHMS AND PESSIMISTIC MODEL-BASED APPROACHES

    … on the statistical error, and 3) a proof of last-iterate global convergence of the proposed algorithm. Lastly, we introduce a model-based offline RL method for confounded POMDPs under general function approximations, which is provably efficient under the assumption of partial coverage imposed …

    jhu Repository record for OFFLINE REINFORCEMENT LEARNING FOR MDPS AND CONFOUNDED POMDPS: POLICY GRADIENT ALGORITHMS AND PESSIMISTIC MODEL-BASED APPROACHES (opens in a new tab) Embargoed until 2029-05-01

  10. Understanding the role of averaging in non-smooth stochastic gradient descent

    … gradient descent (SGD), the error of the final iterate is O(log⁡T⁄T) with high probability. We also construct a function from this class for which the error of the final iterate of deterministic gradient descent is Ω(log⁡T⁄T). This shows that the upper bound is tight and that, in this setting, …

    ubc Repository record for Understanding the role of averaging in non-smooth stochastic gradient descent (opens in a new tab) Download PDF for Understanding the role of averaging in non-smooth stochastic gradient descent (opens in a new tab)

  11. Nonparametric sparse learning of dynamical systems

    … guarantees in the batch learning scenario and last-iterate convergence guarantees in the online case with streaming samples. To illustrate the efficacy of our sparse learning approach, we empirically examine the algorithm through deterministic and stochastic nonlinear system examples. We …

    uiuc Repository record for Nonparametric sparse learning of dynamical systems (opens in a new tab)

  12. Provably efficient algorithms for decentralized optimization

    … method with double averaging that guarantees the last iterate convergence, which is crucial to solving decentralized dual Lagrangian problems with convergence rate guarantee. Chapter 4 studies the composite cost-coupled decentralized optimization in stochastic networks, for which existing …

    uvic Repository record for Provably efficient algorithms for decentralized optimization (opens in a new tab)

  13. On Convergence Analysis of Stochastic and Distributed Gradient-Based Algorithms

    … average of the squared gradient, as well as the last iterations of the algorithm converges to zero almost surely. We also provide a last-iterate almost sure convergence rate analysis for this method on general convex smooth functions. Another aspect of the research addresses the convergence rate …

    waterloo Repository record for On Convergence Analysis of Stochastic and Distributed Gradient-Based Algorithms (opens in a new tab)

  14. Study on the effect of misinformation in multi-agent systems

    … using best-response strategies, that guarantees last-iterate convergence for zero-sum games with a unique Nash equilibrium. Next, we consider the case of misinformation games where the misinformation is due to random noise that additively distorts the payoff matrices of the agents (e.g., due to …

    greece Repository record for Study on the effect of misinformation in multi-agent systems (opens in a new tab)