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 177 for “"gradient methods"”.
-
RESTARTING POLICIES FOR ACCELERATED GRADIENT METHODS
Η παρούσα διπλωματική εργασία έχει ως σκοπό να παράσχει μία αυτοτελή περιγραφή της μεθόδου βελτιστοποίησης με επιτάχυνση και της heavy-ball μεθόδου με επανεκκίνηση. Στο πρώτο μέρος της εισάγονται οι μέθοδοι πρώτης τάξης για βελτιστοποίηση λείων κυρτών συναρτήσεων, η ιδιότητα καθόδου και οι …
-
Knowledge Gradient Methods for Bayesian Optimization
… study in detail how the concept of the knowledge gradient (KG) can be adopted to design novel Bayesian optimization algorithms. First, we propose a novel parallel Bayesian optimization algorithm by generalizing the concept of KG from the fully sequential setting to the parallel setting (qKG). By …
-
Polynomial Preconditioning for Conjugate Gradient Methods
… hermitian positive definite (hpd), the conjugate gradient method of Hestenes and Stiefel is popular. When A is hermitian indefinite (hid), the conjugate residual method may be used. If A is ill-conditioned, these methods may converge slowly, in which case a preconditioner is needed. In this thesis …
-
Policy gradient methods for linear quadratic problems
… results on the theoretical convergence of policy gradient methods, which are the basis of many reinforcement learning algorithms, in both single-agent and multi-agent linear quadratic problems.</p> <p>In the single-agent setting, we show the global convergence of such methods to the optimal …
-
Gradient Methods for Membrane-Mediated Particle Interactions
… develop and apply robust numerical optimization methods for computing stationary particle configurations. Correspondingly, an additional focus is the derivation of a numerically accessible representation of the gradient, including its discretization and relevant numerical analysis. The proof of …
-
Stochastic Gradient Methods with Bias and Momentum
… investigates stochastic optimization methods where exact gradient computations are prohibitively expensive, necessitating potentially biased gradient estimators. Such challenges arise in applications like empirical risk minimization in machine learning, where unbiased gradient …
-
Optimum System Modelling Using Recent Gradient Methods
<p> A study of gradient optimization techniques, in particular as applied to system modelling problems, is made. Three efficient techniques are used to derive optimum second-order and third-order models for a seventh-order system. The optimization techniques are the Fletcher-Powell method, a more …
-
Policy Gradient Methods: Variance Reduction and Stochastic Convergence
… to perform well in a given environment. Policy gradient methods consider a parameterized class of policies, and using a policy from the class, and a trajectory through the environment taken by the agent using this policy, estimate the performance of the policy with respect to the parameters. …
-
APPLYING POLICY GRADIENT METHODS TO OPEN-ENDED DOMAINS
… outside of toy research environments. Modern RL methods still struggle in stochastic, sparse-reward environments with long planning horizons. This thesis studies these challenges from multiple perspectives to develop a stronger empirical understanding of curriculum learning in complex …
-
A Comparative Study of Non Linear Conjugate Gradient Methods
We study the development of nonlinear conjugate gradient methods, Fletcher Reeves (FR) and Polak Ribiere (PR). FR extends the linear conjugate gradient method to nonlinear functions by incorporating two changes, for the step length αk a line search is performed and replacing the residual, rk …
-
Preconditioned conjugate gradient methods for the Navier-Stokes equations
A generalized Conjugate Gradient like method is used to solve the linear systems of equations formed at each time-integration step of the unsteady, two-dimensional, compressible Navier-Stokes equations of fluid flow. The Navier-Stokes equations are cast in an implicit, upwind finite-volume, flux …
-
Preconditioned gradient methods for solving nonlinear underdetermined least-squares problems
… and numerical investigation of preconditioning methods for gradient schemes for solving underdetermined nonlinear least-squares problems. In particular, problems with zero residual are considered, which are equivalent to the problem of solving underdetermined nonlinear systems of equations. …
-
Gradient Methods for Large-Scale and Distributed Linear Quadratic Control
This thesis considers methods for synthesis of linear quadratic controllers for large-scale, interconnected systems. Conventional methods that solve the linear quadratic control problem are only applicable to systems with moderate size, due to the rapid increase in both computational time and …
-
Inverse Problems for the Heat Equation Using Conjugate Gradient Methods
… method is employed to obtain their Fréchet gradients with respect to the unknown quantities. Based on this gradient, the conjugate gradient method (CGM) is established together with the adjoint and sensitivity problems. The stability of the numerical solution is investigated by introducing …
-
New Preconditioned Conjugate Gradient Methods for Some Structured Problems in Physics
… and analysis of new preconditioned conjugate gradient (PCG) algorithms for three important classes of large-scale and complex physical problems characterized by special structures. We propose several new iterative methods for solving the eigenvalue problem or energy minimization problem, which …
-
Reinforcement Learning Policy Gradient Methods for Reservoir Operation Management and Control
… various novel DRL continuous-action policy gradient methods (PGMs), including Deep Deterministic Policy Gradients (DDPG), Twin Delayed DDPG (TD3), and two different versions of Soft Actor-Critic (SAC18 and SAC19) to identify optimal reservoir operation policy for the Folsom Reservoir located …
Page 1 of 9