Random matrix analysis to balance between supervised and unsupervised learning under the low density separation assumption
V Feofanov, M Tiomoko… - … Conference on Machine …, 2023 - proceedings.mlr.press
We propose a theoretical framework to analyze semi-supervised classification under the low
density separation assumption in a high-dimensional regime. In particular, we introduce …
density separation assumption in a high-dimensional regime. In particular, we introduce …
Enhancing Multivariate Time Series Forecasting via Multi-Task Learning and Random Matrix Theory
We present a novel approach to multivariate time series forecasting by framing it as a multi-
task learning problem. We propose an optimization strategy that enhances single-channel …
task learning problem. We propose an optimization strategy that enhances single-channel …
Random matrix theory and concentration of the measure theory for the study of high dimension data processing.
C Louart - 2023 - theses.hal.science
The main objective of this thesis is to introduce a probabilistic framework taken from the
theory of concentration of measure to study of machine learning algorithms. The …
theory of concentration of measure to study of machine learning algorithms. The …
A Concentration of Measure Framework to study convex problems and other implicit formulation problems in machine learning
C Louart - arXiv preprint arXiv:2010.09877, 2020 - arxiv.org
This paper provides a framework to show the concentration of solutions $ Y^* $ to convex
minimizing problem where the objective function $\phi (X)(Y) $ depends on some random …
minimizing problem where the objective function $\phi (X)(Y) $ depends on some random …