- Universidade Aberta de Portugal
- Biblioteca Digitais de Teses e Dissertações da USP
- University of Limerick
- Biblioteca Digital da Unicamp
- Universidade de Lisboa
- Universidade Cornell
- Universidade Duke
- London School of Economics and Political Science Research
- Maths, Stats & OR Network
- The Higher Education Academy
- SA Journal of Industrial Psychology
- Mais Publicadores...

## Desafios e perspetivas do ensino da matemática no ensino superior online : um estudo de caso

## O ensino de estatística e a busca do equilíbrio entre os aspectos determinísticos e aleatórios da realidade; The teaching of statistics and the search for the equilibrium between deterministic and random aspects of reality

## An investigation into the teaching and learning of probability at senior cycle

## A formação estatistica e pedagogica do professor de matematica em comunidades de pratica; The formation pedagogy and statistic of the teacher of mathematics in communities of practice

## Come away with me: Statistics learning through collaborative work

## Efficient Mixed-Norm Regularization: Algorithms and Safe Screening Methods

## Adaptivity and Computation-Statistics Tradeoffs for Kernel and Distance based High Dimensional Two Sample Testing

## $\ell_p$ Testing and Learning of Discrete Distributions

## On the Robustness of Regularized Pairwise Learning Methods Based on Kernels

## Two-stage Sampled Learning Theory on Distributions

## Fast and Flexible ADMM Algorithms for Trend Filtering

## M@th Desktop and MD Tools - Mathematics and Mathematica Made Easy for Students

## Distributed Clustering and Learning Over Networks

## Learning Theory for Distribution Regression

## Missing Entries Matrix Approximation and Completion

## Dimensionality Reduction and Learning on Networks

Machine learning is a powerful branch of mathematics and statistics that allows the automation of tasks that would otherwise require humans a long time to perform. Two particular fields of machine learning that have been developing in the last two decades are dimensionality reduction and semi-supervised learning.

Dimensionality reduction is a powerful tool in the analysis of high dimensional data by reducing the number of variables under consideration while approximately preserving some quantity of interest (usually pairwise distances). Methods such as Principal Component Analysis (PCA) or Isometric Feature Mapping (ISOMAP) do this do this by embedding the data, equipped with a nonnegative, symmetric, similarity kernel or adjacency matrix into Euclidean space and finding a linear subspace or low dimensional submanifold which best fits the data, respectively.

When the data takes the form of network data, how to perform such dimensionality reduction intrinsically, without resorting to an embedding, that can be extended to the case of nonnegative, non-symmetric adjacency matrices remains an important open problem. In the first part of my dissertation, using current techniques in local spectral clustering to partition the network using a Markov process induced by the adjacency matrix...