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 9 of 9 for “"Mirror descent algorithm"”.
-
A Control-theoretical Analysis of Continuous-time Distributed Mirror Descent Algorithm
… We study a continuous-time decentralized mirror descent algorithm that uses purely local gradient information to converge to the global optimal solution. The algorithm enforces consensus among agents using the idea of {\it integral feedback}, allowing the system to converge with a constant …
-
Bregman generalized subgradient projected algorithms and applications
… subgradient methods were thought as ideal algorithms for constrained minimization problems. But they are often hampered by the computational complexity of the projection operator. The generalized Bregman distance has been identified as a potential solution to this issue. This thesis delves …
-
Inference on Markov random fields: methods and applications
… the computational complexity of inference algorithms. First, we consider the smoothing problem on Hidden Markov Models (HMMs) and discuss novel algorithms that have sub-quadratic computational complexity in the number of particles used. We show they perform on par with existing …
-
Stochastic Methods in Model Estimation: New Algorithms and New Properties
We study the properties of applying stochastic algorithms to solve optimization problems in model estimation. In particular, we investigate the statistical properties of estimators that are based on some stochastic algorithms in Chapters 2, 3, 4, and 5; we propose a new stochastic algorithm and …
-
Improving Online Mirror Descent for Convex Optimization in Dynamic Environments
… application domains. One of the most popular algorithms in solving OCO problems is online mirror descent. Interesting theoretical and practical properties have made online mirror descent a powerful tool in solving large-scale and high-dimensional problems. However, the existing works on online …
-
Geometry-Informed Sampling and Estimation for Constrained Statistical Inference
… theoretical analysis of the stochastic projected mirror descent algorithm. This algorithm is of particular interest as it is domain-aware by regularizing using Bregman divergences while also allowing for additional external constraints. After establishing asymptotic consistency using the ODE …
-
Nonparametric Box-Cox model in high-dimensional regression
… efficiently by using a coordinate-majorization-descent algorithm. Extensive simulation studies show that the proposed method performs well in various settings. Our analysis of the supermarket data demonstrates the superior performance of the proposed method over the standard high-dimensional …
-
Nonparametric Box-Cox model in high-dimensional regression
… efficiently by using a coordinate-majorization-descent algorithm. Extensive simulation studies show that the proposed method performs well in various settings. Our analysis of the supermarket data demonstrates the superior performance of the proposed method over the standard high-dimensional …
-
Online EM for Exponential Family Distributions
The expectation-maximization (EM) algorithm is a widely utilized method for fitting probabilistic models with missing data or latent variables. However, applying the EM algorithm to high-dimensional datasets requires storing the entire dataset in computer memory, which is necessary at each …