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 20 for “"Frank-Wolfe algorithm"”.

  1. JAVA Animated Software for Teaching the Frank-Wolfe Algorithm for Static Traffic Network Equilibrium

    The popular Frank-Wolfe (FW) algorithm for solving the network equilibrium problems plays an important role in transportation simulation. Not only has the basic Frank Wolfe algorithm been studied, but also other variations of the FW algorithm (such as Conjugate Frank Wolfe and Bi-Conjugate Frank …

    odu Repository record for JAVA Animated Software for Teaching the Frank-Wolfe Algorithm for Static Traffic Network Equilibrium (opens in a new tab)

  2. Optimization Methods for Semi-Supervised Learning

    … this thesis is to provide efficient optimization algorithms for some semi-supervised learning (SSL) tasks in machine learning. For many machine learning tasks, training a classifier requires a large amount of labeled data; however, providing labels typically requires costly manual annotation. …

    waterloo Repository record for Optimization Methods for Semi-Supervised Learning (opens in a new tab)

  3. Selecting and scheduling of improvements in urban transportation networks using metaheuristics

    … the costs of network flows determined with the Frank-Wolfe algorithm, which is modified to consider intersection flows and delays. Intersections are modelled with pseudo-links. The methods used for choosing the optimal schedule of project improvements are: Ant Colony Optimization, Simulated …

    maryland Repository record for Selecting and scheduling of improvements in urban transportation networks using metaheuristics (opens in a new tab)

  4. Frank-Wolfe Methods for Optimization and Machine Learning

    In Chapter 2, we present the Frank-Wolfe algorithm (FW) and all necessary background material. We explain the projection-free and sparsity properties of the algorithm, provide motivation for real-world problems, and analyze the convergence rates and a lower bound on the complexity. In Chapter 3, we …

    gatech Repository record for Frank-Wolfe Methods for Optimization and Machine Learning (opens in a new tab)

  5. Work Zone Analysis Under Detour Settings

    … the traffic. To solve for User Equilibrium, the Frank-Wolfe algorithm is implemented via Matlab. The total delay cost is then converted to a monetary value using value of time (VOT). The work zone set-up cost and accident cost relate to number of work zone segments and total length of work zone. …

    cornell Repository record for Work Zone Analysis Under Detour Settings (opens in a new tab)

  6. Parallel Implementations of the Frank-Wolfe Algorithms for the Traffic Assignment Problem

    … The traffic assignment problem is one algorithm of great importance to planners because it provides insight into how traffic will flow within the network. The Frank-Wolfe algorithm is a traditional solution method for this optimization problem, but it has been characterized by its slow …

    odu Repository record for Parallel Implementations of the Frank-Wolfe Algorithms for the Traffic Assignment Problem (opens in a new tab)

  7. Prediction in High-Dimensional Statistical Modelling Using Greedy Algorithms and Information Theoretic Criteria

    … model). It has been shown that the greedy algorithms e ciently generate models in the HD case as well as in the big data (BD) case (n pn). We discuss the use of the following greedy algorithms: Matching Pursuit Algorithm (MPA), Orthogonal Matching Pursuit (OMP), Relaxed Matching Pursuit …

    auckland-ms Repository record for Prediction in High-Dimensional Statistical Modelling Using Greedy Algorithms and Information Theoretic Criteria (opens in a new tab)

  8. Robust Approaches for Matrix-Valued Parameters

    … of matrix operations, we propose to apply the Frank-Wolfe algorithm, a first-order algorithm for optimization on a restricted region with low computation burden per iteration. Theoretically, we establish finite-sample error bounds under high-dimensional settings. We show that the estimation …

    temple Repository record for Robust Approaches for Matrix-Valued Parameters (opens in a new tab)

  9. Kernel Methods for Graph-structured Data Analysis

    … matching, for all of which we propose effective algorithms by making use of kernel functions and the corresponding reproducing kernel Hilbert spaces.For the first topic, we develop effective graph kernels, named as "RetGK," for quantitatively measuring the similarities between graphs. Graph …

    wustl Repository record for Kernel Methods for Graph-structured Data Analysis (opens in a new tab)

  10. A Dual Toll Policy for Regulating the Transportation of Hazardous Materials

    … terms into linear ones. The other applies the Frank-Wolfe algorithm, an iterative first-order optimization algorithm. Then a genetic-algorithm-based methodology will integrate both levels. Computational experiments on different sizes of networks are performed to demonstrate the effectiveness of …

    waterloo Repository record for A Dual Toll Policy for Regulating the Transportation of Hazardous Materials (opens in a new tab)

  11. Multi-commodity flow estimation with partial counts on selected links

    … and linear network constraints. The modified Frank-Wolfe algorithm, which is a type of conditional gradient method, is used to solve the assignment problem. The next step is to consider both of the observed traffic counts on selected links and the deterministic user equilibrium assignments on …

    tamu Repository record for Multi-commodity flow estimation with partial counts on selected links (opens in a new tab)

  12. Module Identification for Biological Networks

    … In this dissertation, we propose computational algorithms to overcome those challenges. To identify functional modules based on interaction patterns, we develop efficient algorithms based on the concept of block modeling. We propose a subgradient Frank-Wolfe algorithm with path generation method …

    tamu Repository record for Module Identification for Biological Networks (opens in a new tab)

  13. Scalable Learning and Energy Management for Power Grids

    … In this context, the present thesis pioneers algorithmic innovations targeting timely opportunities emerging with future power systems in terms of learning, load control, and microgrid management. Our vision is twofold: advancing algorithms and their performance analysis, while contributing …

    umn Repository record for Scalable Learning and Energy Management for Power Grids (opens in a new tab)

  14. Modern Adaptive Experiment Design: Machine Learning Perspective

    … relaxation techniques. We introduce a master algorithm and its linearized form based on the Frank-Wolfe algorithm, applicable to general experimental design problems. This algorithm is demonstrated in applications involving various utilities, including reward minimization and information …

    ethz Repository record for Modern Adaptive Experiment Design: Machine Learning Perspective (opens in a new tab)

  15. Attacks and Defenses in Privacy-Preserving Representation Learning

    … (MOO) and propose a multiple-gradient descent algorithm that enables the efficient application of the Frank-Wolfe algorithm to search for the optimal utility-privacy configuration of the text classification task. Graph neural networks (GNNs) combine the representational power of neural networks …

    ttu Repository record for Attacks and Defenses in Privacy-Preserving Representation Learning (opens in a new tab)

  16. Bridging Discrete and Continuous Methods for Faster Optimization and Machine Learning

    … age we are in, it has become commonplace for algorithms to make decisions that impact our lives. Many such algorithms use optimization solvers as a subroutine, and there has been a revived interest in using robust approaches (like first-order optimization methods) that require low memory …

    gatech Repository record for Bridging Discrete and Continuous Methods for Faster Optimization and Machine Learning (opens in a new tab)

  17. An Efficient Ranking and Classification Method for Linear Functions, Kernel Functions, Decision Trees, and Ensemble Methods

    Structural algorithms incorporate the interdependence of outputs into the prediction, the loss, or both. Frank-Wolfe optimizations of pairwise losses and Gaussian conditional random fields for multivariate output regression are two such structural algorithms. Pairwise losses are standard 0-1 …

    temple Repository record for An Efficient Ranking and Classification Method for Linear Functions, Kernel Functions, Decision Trees, and Ensemble Methods (opens in a new tab)

  18. Smoothed analysis in Nash equilibria and the Price of Anarchy

    São analisados nesta dissertação problemas em teoria dos jogos, com enfoque no efeito que perturbações acarretam em jogos. A análise suavizada (smoothed analysis) é utilizada para tal análise, e dois tipos de jogos são o foco principal desta dissertação, jogos bimatrizes e o problema de atribuição …

    brazil-ufrgs Repository record for Smoothed analysis in Nash equilibria and the Price of Anarchy (opens in a new tab)

  19. Theoretical Guarantees for Bayesian Generalized Linear Regression And Variational Boosting

    … family. We employ a functional version of Frank-Wolfe optimization as our variational algorithm and study frequentist properties of the iterative boosting updates. Comparisons are drawn to the recent literature on boosting, describing how the choice of the variational family and the …

    tamu Repository record for Theoretical Guarantees for Bayesian Generalized Linear Regression And Variational Boosting (opens in a new tab)

  20. Some Algorithms for Large-Scale Linear and Convex Minimization in Relative Scale

    This thesis is concerned with the study of algorithms for approximately solving large-scale linear and nonsmooth convex minimization problems within a prescribed relative error $\delta$ of the optimum. The methods we propose converge in $O(1/\delta^2)$ or $O(1/\delta)$ iterations of a first-order …

    cornell Repository record for Some Algorithms for Large-Scale Linear and Convex Minimization in Relative Scale (opens in a new tab)