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 291 for “"Convergence analysis"”.
-
Convergence Analysis of Segmental Refinement Multigrid
… number of levels. My work provides a theoretical analysis and practical implementation demonstrating the root cause of SRMG’s previous failures was due to the underlying low-communication mechanisms of the algorithm. My concluding analysis demonstrates future potential for SRMG, although it …
-
Convergence analysis of the immersed boundary method.
… regularizations of delta functions. We study the convergence properties of such discretizations for constant coefficient elliptic problems using the Immersed Boundary (IB) method, which is both a mathematical formulation and a numerical scheme widely used to solve fluid-structure interaction …
-
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 …
-
Convergence analysis of training deep linear neural networks
… a stepsize and a gradient. We provide a detailed analysis of the underlying GD dynamics and devise a bound that controls the growth of GD iterates and the underlying gradient throughout the learning phase. In particular, we prove GD convergence to a critical point for linear neural networks. We …
-
A Convergence Analysis of Generalized Hill Climbing Algorithms
… and tabu search. A necessary and a sufficient convergence condition for GHC algorithms are presented. The convergence conditions presented in this dissertation are based upon a new iteration classification scheme for GHC algorithms. The convergence theory for particular formulations of GHC …
-
Convergence analysis for out-of-core temporal difference learning
… Markovian sampling assumptions of classical RL convergence theory. This thesis resolves this disconnect by providing a novel convergence analysis of Temporal Difference (TD) learning under a cyclic streaming paradigm. Because cyclic scanning is deterministic, our analysis isolates and bounds the …
-
Convergence Analysis of Discontinuous Galerkin Methods for Poroelasticity Equations
… penalty term in the scheme. Theoretical convergence error estimates derived in a discrete-in-time setting show the a priori error can be bounded by some constant, which is related to the pressure, displacement, dilatation and the mesh size.
-
A Convergence Analysis of LDPC Decoding Based on Eigenvalues
… implementation of LDPC codes. Relatively slow convergence of iterative decoding algorithm affects the performance of LDPC codes. Faster convergence can be achieved by reducing the number of iterations during the decoding process. In this thesis, a new approach for faster convergence is …
-
An adaptive asynchronous CDMA receiver and its convergence analysis
… to changes in the power of the users. Tile convergence and transient behavior of the receiver are also investigated and found to have similar results to its synchronous counterpart. A new way to analyze the error performance of the decorrelator is also proposed and the error probability of …
-
Convergence Analysis of the Modified Chebyshev-Picard Iteration Algorithm
The topic of this thesis is the analysis of the ability of Modified Chebyshev-Picard Iteration (MCPI) to converge on an accurate solution. The convergence analysis includes a discussion of MCPI and a brief explanation of the derivation of first and second order MCPI. The limitations and benefits of …
-
Quantitative convergence analysis of dynamical processes in machine learning
This thesis focuses on analyzing the quantitative convergence of selected important machine learning processes, from a dynamical perspective, in order to understand and guide machine learning practices. Machine learning is becoming increasingly popular in various fields. Typical machine learning …
-
On Convergence Analysis of Stochastic and Distributed Gradient-Based Algorithms
… a concise and rigorous proof of the almost sure convergence guarantees towards a critical point in the context of smooth and non-convex objective functions. To the best of our knowledge, this work offers the first almost sure convergence rates for these stochastic adaptive gradient-based methods. …
-
Convergence analysis for finite element discretizations of highly indefinite problems
… is an important topic of research in numerical analysis to find an efficient numerical discretization which behaves reasonably robust with respect to the wave number. One of the interesting questions in this area is how the performance of the method can be affected by the parameters like the …
-
Convergence Analysis and Improvements for Projection Algorithms and Splitting Methods
… iterating this operator eventually results in convergence to an optimal point. However, as for other first order methods, the convergence rate is heavily dependent on the conditioning of the problem. Even though the per-iteration cost is usually low, the number of iterations can become …
-
The Bounded-SOS+SONC Relaxation: Theory, Convergence Analysis, and Implementation
Polynomial optimization is a class of global optimization problems defined by real polynomials, with applications in power systems, portfolio optimization and control theory. At the heart of polynomial optimization lies the problem of certifying the global nonnegativity of polynomials. Algebraic …
-
The QOBE algorithm : stochastic convergence analysis and application to classification
Thesis (Ph. D.)--Michigan State University, Department of Electrical and Computer Engineering, 2003
Page 1 of 15