Essays about: "uniform convergence"

Showing result 1 - 5 of 13 essays containing the words uniform convergence.

1. 1. Stochastic Frank-Wolfe Algorithm : Uniform Sampling Without Replacement

   University essay from Umeå universitet/Institutionen för matematik och matematisk statistik

   Author : Olof Håkman; [2023]
   Keywords : Stochastic Frank-Wolfe; Stochastic optimization; Sampling without replacement;

   Abstract : The Frank-Wolfe (FW) optimization algorithm, due to its projection free property, has gained popularity in recent years with typical application within the field of machine learning. In the stochastic setting, it is still relatively understudied in comparison to the more expensive projected method of Stochastic Gradient Descent (SGD). READ MORE

3. 2. An Introduction to Metric Spaces

   University essay from Linköpings universitet/Analys och didaktik; Linköpings universitet/Tekniska fakulteten

   Author : Samuel Erickson Andersson; David Wiman; [2022]
   Keywords : Analysis; compact; convergence; limit; metric space; sequence; set; topology; Analys; följd; gränsvärde; kompakt; konvergens; metriskt rum; mängd; topologi;

   Abstract : In this thesis we start off by ensuring that the reader is up to speed when it comes to some well known definitions and theorems from real analysis. We then introduce the reader to metric spaces and provide them with some examples such as the real numbers with the Euclidean distance, and compact sets with the Hausdorff distance. READ MORE

4. 3. Data-Driven Motion Planning : With Application for Heavy Duty Vehicles

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Oscar Palfelt; [2022]
   Keywords : Motion planning; Deep learning; Autonomous driving; Nonuniform sampling; Rörelseplanering; Djupinlärning; Autonom körning; Ojämn provtagning;

   Abstract : Motion planning consists of finding a feasible path of an object between an initial state and a goal state, and commonly constitutes a sub-system of a larger autonomous system. Motion planners that utilize sampling-based algorithms create an implicit representation of the search space via sampling said search space. READ MORE

5. 4. The Dynamics of Neural Networks Expressivity with Applications to Remote Sensing Data

   University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Author : Hui Zhang; [2022]
   Keywords : Neural Networks; Linear Regions; Expressivity; Initialization; Remote Sensing; Neurala nätverk; linjära regioner; uttrycksfullhet; initialisering; fjärranalys;

   Abstract : Deep neural networks (DNN) have been widely demonstrated to be more powerful than their shallower counterparts in a variety of computer vision tasks and remote sensing applications. However, as many techniques are based on trial-and-error experiments as opposed to systematic evaluation, scientific evidence for the superiority of DNN needs more theoretical and experimental foundations. READ MORE

6. 5. Discrepancy of sequences and error estimates for the quasi-Monte Carlo method

   University essay from Karlstads universitet

   Author : Niklas Vesterinen; [2020]
   Keywords : discrepancy; low discrepancy sequences; van der Corput; quasi-Monte Carlo; Koksma inequality; error estimates; diskrepans; lågdiskrepanstalföljder; van der Corput; kvasi-Monte Carlo; Koksmas olikhet; feluppskattningar;

   Abstract : We present the notions of uniform distribution and discrepancy of sequences contained in the unit interval, as well as an important application of discrepancy in numerical integration by way of the quasi-Monte Carlo method. Some fundamental (and other interesting) results with regards to these notions are presented, along with some detalied and instructive examples and comparisons (some of which not often provided by the literature). READ MORE