Clicking on any of the links below will redirect you to the abstract and details of my contributions.
We developed a generative framework based on extremal principal component analysis to estimate extreme precipitation event probabilities, addressing the tasks of the Data Challenge at the 14th Conference on Extreme Value Analysis.
To reduce the dimensionality of multivariate data residing on graphs, we propose a principal component analysis in the graph frequency domain.
We proposed a new decomposition method for graph signals.
We defined new causal estimands and estimators on metric spaces.
To reduce the dimensionality of multivariate data residing on graphs, we propose a graph frequency-domain factor model.
We proposed a quantile based fitting method for analyzing graph signals.
We proposed a cross-spectral analysis tool for bivariate graph signals.
We presented several semiparametric approaches for the inference of univariate and multivariate extremes to resolve the tasks from the Data Challenge at the 13th Conference on Extreme Value Analysis.
To predict wafer performance using OES data, we propose a prediction method based on a functional approach using multivariate functional partial least squares regression, coupled with dimension reduction and a novel outlier detection technique via functional independent component analysis.
We proposed a novel method for forecasting network time series.
We performed a PCA on river network data.